© 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. 10204
    Prev
    Next
    INDEX
    Explanations

    numeric data expressed in various formats

    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
    +0.23
    1.3%
    255
    +0.13
    0.7%
    335
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.23
    0.02
    255
    +0.13
    -0.00
    397
    +0.10
    0.07
    Negative Logits
    .";
    -2.33
    ";
    -2.17
    "];
    -1.88
    .*;
    -1.83
    than
    -1.80
     than
    -1.75
     ();
    -1.72
    ”;
    -1.68
     (“
    -1.63
    ();
    -1.63
    POSITIVE LOGITS
    ·¸
    3.67
    )_
    3.59
    )"
    3.58
    ¬
    3.47
    ª
    3.41
    ¨
    3.40
     *)
    3.39
    )."
    3.37
    !)
    3.34
    »
    3.34
    Activations Density 1.030%

    No Known Activations