© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 11251
    Prev
    Next
    INDEX
    Explanations

    references to quantities and measurements

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    78
    +0.14
    0.8%
    348
    +0.14
    0.8%
    63
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    431
    +0.14
    0.05
    500
    +0.14
    0.04
    295
    +0.12
    0.04
    Negative Logits
    batim
    -1.52
    ETHOD
    -1.50
     Comedy
    -1.35
     Videos
    -1.28
     afternoon
    -1.26
     artist
    -1.24
    html
    -1.24
    bool
    -1.23
     fun
    -1.19
    rass
    -1.19
    POSITIVE LOGITS
    Ĭ
    2.85
    ī
    2.77
    §
    2.74
    ↵↵
    2.72
    ↵↵
    2.72
    č↵
    2.72
    <|outofrange|>
    2.72
           ↵
    2.72
    2.72
    ↵↵
    2.72
    Activations Density 0.285%

    No Known Activations