© 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. 10863
    Prev
    Next
    INDEX
    Explanations

    content related to advertisements and user interactions with websites

    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
    456
    +0.12
    0.7%
    263
    +0.12
    0.7%
    359
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    329
    +0.12
    0.03
    103
    +0.12
    0.04
    456
    +0.11
    0.03
    Negative Logits
    .’
    -1.51
    ating
    -1.51
    !’
    -1.48
    ori
    -1.47
    .’”
    -1.45
    anting
    -1.44
    dess
    -1.41
    !'
    -1.40
     parliament
    -1.38
    ising
    -1.32
    POSITIVE LOGITS
    ureus
    1.66
    º
    1.65
    ¡
    1.61
    ĥ½
    1.58
                                       
    1.57
    <|outofrange|>
    1.57
                              
    1.57
    <|outofrange|>
    1.57
                                 
    1.57
    ↵↵    
    1.57
    Activations Density 0.180%

    No Known Activations