© 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. 30317
    Prev
    Next
    INDEX
    Explanations

    topics related to entertainment media and culture

    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
    156
    +0.55
    3.8%
    111
    +0.34
    2.3%
    5
    +0.08
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.55
    0.59
    111
    +0.34
    0.57
    4
    +0.08
    0.56
    Negative Logits
    ·
    -2.39
    <|outofrange|>
    -2.18
                                               
    -2.18
    ↵                      
    -2.18
    <|outofrange|>
    -2.18
    č↵      
    -2.18
    ↵	  
    -2.18
    <|outofrange|>
    -2.18
    ↵            ↵           
    -2.18
                                                          
    -2.18
    POSITIVE LOGITS
    ensive
    1.43
    atics
    1.30
    ovascular
    1.26
    beit
    1.25
     arms
    1.23
    ="
    1.22
    ^](#
    1.22
    rait
    1.20
    anguage
    1.19
    aline
    1.16
    Activations Density 2.070%

    No Known Activations