© 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. 9415
    Prev
    Next
    INDEX
    Explanations

    references to biological mechanisms and their regulatory roles

    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
    498
    +0.13
    0.7%
    235
    +0.12
    0.7%
    5
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.13
    0.02
    401
    +0.12
    0.01
    235
    +0.11
    0.02
    Negative Logits
    ¥
    -1.93
    Ĥ¬
    -1.82
    ľĵ
    -1.82
    »¿
    -1.77
    ½
    -1.77
    ²
    -1.68
    catalina
    -1.65
    ↵↵
    -1.62
    č↵č↵
    -1.62
    -1.62
    POSITIVE LOGITS
     underlying
    2.68
     mediating
    2.64
     responsible
    2.58
     behind
    2.35
     involved
    2.29
     regulating
    2.25
     governing
    2.24
     whereby
    2.22
     implicated
    2.15
     controlling
    2.15
    Activations Density 0.095%

    No Known Activations