© 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. 9823
    Prev
    Next
    INDEX
    Explanations

    elements related to database attributes and user information structures

    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
    +0.16
    1.0%
    25
    +0.16
    1.0%
    466
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    299
    +0.16
    0.15
    466
    +0.16
    0.20
    9
    +0.14
    0.08
    Negative Logits
     =>
    -1.78
     strengths
    -1.42
    sembles
    -1.30
     <-
    -1.28
    wordpress
    -1.25
    cule
    -1.24
     philosophy
    -1.20
    waukee
    -1.17
     weaknesses
    -1.15
     concept
    -1.10
    POSITIVE LOGITS
    .");
    2.39
    )</
    2.38
    ).](
    2.38
    )\].
    2.37
    .'"
    2.32
    )."
    2.21
    )].
    2.20
    .’”
    2.18
    "}\].
    2.17
    .](
    2.15
    Activations Density 7.339%

    No Known Activations