© 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. 1-RES-SM
    11. 28619
    Prev
    Next
    INDEX
    Explanations

    instances of the word "present."

    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
    39
    +0.20
    1.1%
    187
    +0.12
    0.7%
    467
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    39
    +0.20
    0.02
    187
    +0.12
    0.02
    112
    +0.11
    0.01
    Negative Logits
     plain
    -1.81
    ichlet
    -1.65
     integrity
    -1.35
     payable
    -1.35
     blocks
    -1.34
     matching
    -1.33
     "_
    -1.32
     php
    -1.32
     ${
    -1.29
    Signature
    -1.23
    POSITIVE LOGITS
    ¨
    2.57
    ł
    2.46
    ĥ
    2.41
    ĸ
    2.38
    Ŀ
    2.35
    ĵ
    2.33
    ķ
    2.31
    ĨĴ
    2.30
    Ł
    2.26
    ī
    2.25
    Activations Density 0.026%

    No Known Activations