© 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. 1-RES-SM
    11. 25252
    Prev
    Next
    INDEX
    Explanations

    references to the human body and its related concepts

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    356
    +0.14
    0.8%
    144
    +0.12
    0.7%
    71
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    356
    +0.14
    0.03
    93
    +0.12
    0.03
    144
    +0.11
    0.03
    Negative Logits
    hift
    -1.84
     behalf
    -1.78
     her
    -1.67
    ĨĴ
    -1.65
    ield
    -1.64
    ª
    -1.62
     confidential
    -1.60
     young
    -1.59
     morning
    -1.57
     afternoon
    -1.55
    POSITIVE LOGITS
    weight
    2.12
    guard
    2.06
    guards
    2.05
    builder
    1.96
    piece
    1.94
    bones
    1.77
    work
    1.74
    pieces
    1.74
    building
    1.73
    fat
    1.73
    Activations Density 0.101%

    No Known Activations