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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 13757
    Prev
    Next
    INDEX
    Explanations

    references to legal codes and statutes

    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
    326
    +0.14
    0.8%
    161
    +0.12
    0.7%
    92
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.61
    156
    +0.12
    0.55
    71
    +0.11
    0.53
    Negative Logits
    orously
    -1.64
     passage
    -1.59
     completeness
    -1.46
     completion
    -1.41
     [(\[
    -1.34
     finishes
    -1.33
    č↵č
    -1.33
     exploration
    -1.33
     rounds
    -1.32
     skew
    -1.31
    POSITIVE LOGITS
    ĥ½
    1.79
    ·¸
    1.75
    Ļ
    1.67
    ¿½
    1.67
    ¤
    1.66
    Ĩ
    1.64
    rb
    1.63
    perg
    1.58
    ·
    1.52
    Ľ
    1.50
    Activations Density 3.419%

    No Known Activations