© 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. 4-RES-SM
    11. 14450
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and conditions, particularly those involving strings, integers, and their specific manipulations

    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
    307
    +0.24
    1.4%
    466
    +0.16
    0.9%
    348
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    357
    +0.24
    0.05
    17
    +0.16
    0.04
    47
    +0.16
    0.05
    Negative Logits
    ĻĤ
    -2.98
    ¸
    -2.92
    ij
    -2.78
    Ń
    -2.65
    ¼
    -2.60
    ¶
    -2.56
    Ĥ
    -2.55
    »
    -2.55
    ľĵ
    -2.53
    º
    -2.52
    POSITIVE LOGITS
     integers
    2.69
     integer
    2.49
     NaN
    2.14
    Decimal
    2.08
     Integer
    2.06
    NaN
    2.03
     zeros
    2.01
     numbers
    1.97
    Integer
    1.94
    99999999
    1.91
    Activations Density 0.813%

    No Known Activations