© 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. 13902
    Prev
    Next
    INDEX
    Explanations

    numerical values or codes

    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
    397
    +0.19
    1.0%
    78
    +0.14
    0.8%
    151
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.19
    0.05
    9
    +0.14
    0.05
    151
    +0.12
    0.04
    Negative Logits
    .")
    -1.75
    ():
    -1.51
     hats
    -1.48
     periodically
    -1.47
    ,”
    -1.45
    :")
    -1.40
    :--
    -1.36
    ):
    -1.36
    gery
    -1.35
     remotely
    -1.34
    POSITIVE LOGITS
    ĵ
    4.69
    ĥ½
    4.60
    Ļ
    4.42
    Į
    4.31
    Īĺ
    4.26
    Ĥ¬
    4.23
    ı
    4.12
    IJ
    4.11
    Ľ
    4.08
    ĥ
    4.06
    Activations Density 0.457%

    No Known Activations