Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 27017
    Prev
    Next
    INDEX
    Explanations

    keywords related to software licensing

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    23
    +0.19
    1.2%
    53
    +0.15
    1.0%
    478
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.19
    0.06
    273
    +0.15
    0.03
    333
    +0.12
    0.03
    Negative Logits
    zent
    -1.69
    /#
    -1.61
    ém
    -1.51
    ography
    -1.49
     combo
    -1.49
    mog
    -1.49
    ics
    -1.39
     Warriors
    -1.36
    ict
    -1.34
    eric
    -1.34
    POSITIVE LOGITS
    ŀ
    1.90
    Ĥ
    1.87
    »
    1.78
    ģ
    1.72
     ashamed
    1.57
    ĨĴ
    1.56
    ķ
    1.54
    Īĺ
    1.53
    LLOW
    1.53
    ¿½
    1.44
    Activations Density 0.330%

    No Known Activations