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. 27029
    Prev
    Next
    INDEX
    Explanations

    mentions of support and compatibility in various contexts

    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
    443
    +0.16
    0.9%
    4
    +0.14
    0.8%
    415
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    4
    +0.16
    0.02
    443
    +0.14
    0.02
    277
    +0.12
    0.02
    Negative Logits
    isman
    -1.88
    illes
    -1.63
    unter
    -1.51
    sie
    -1.47
    edy
    -1.43
    invasive
    -1.41
    eves
    -1.37
    uks
    -1.36
     Cherokee
    -1.35
    enron
    -1.33
    POSITIVE LOGITS
    ¡
    1.86
    ł
    1.78
    veis
    1.76
    Ļª
    1.74
    Ī
    1.72
    ¦
    1.67
     by
    1.65
    emente
    1.62
    nier
    1.54
    Ħ
    1.53
    Activations Density 0.103%

    No Known Activations