© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 28452
    Prev
    Next
    INDEX
    Explanations

    references to controversial or sensitive topics, particularly related to societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    47
    +0.18
    1.0%
    156
    +0.15
    0.9%
    507
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    424
    +0.18
    0.03
    360
    +0.15
    0.05
    177
    +0.12
    0.05
    Negative Logits
    ĸ´
    -1.82
    ??
    -1.72
    ↵                                    
    -1.71
    <|outofrange|>
    -1.71
    ↵                                                       
    -1.71
                                                     
    -1.71
    <|outofrange|>
    -1.71
             
    -1.71
                                        
    -1.71
                                          
    -1.71
    POSITIVE LOGITS
    irected
    1.91
    igraph
    1.72
    icator
    1.64
    reviewed
    1.49
    =”
    1.44
     combo
    1.44
    pieces
    1.37
     ensemble
    1.36
    imeters
    1.34
    weighted
    1.33
    Activations Density 1.501%

    No Known Activations