© 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. 14545
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to population and demographic trends

    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
    61
    +0.13
    0.7%
    78
    +0.12
    0.7%
    276
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    61
    +0.13
    0.09
    125
    +0.12
    0.07
    30
    +0.11
    0.04
    Negative Logits
    itude
    -1.73
     gameplay
    -1.52
     kindly
    -1.48
    ureus
    -1.46
    release
    -1.33
     quo
    -1.31
    merce
    -1.30
    ]:
    -1.28
    ionine
    -1.28
     xx
    -1.28
    POSITIVE LOGITS
    %
    2.96
     percent
    2.96
    ħ
    2.83
    %,
    2.79
    %--
    2.76
     million
    2.70
     billion
    2.65
    \%$
    2.59
    ł
    2.57
    %.
    2.52
    Activations Density 0.316%

    No Known Activations