© 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. 29721
    Prev
    Next
    INDEX
    Explanations

    mentions of tropical environments or conditions

    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
    156
    +0.23
    1.3%
    438
    +0.12
    0.7%
    304
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    304
    +0.23
    0.02
    448
    +0.12
    0.01
    182
    +0.11
    0.01
    Negative Logits
    zione
    -1.66
    usement
    -1.54
    olean
    -1.53
     blinding
    -1.46
    hav
    -1.45
    oci
    -1.45
    ceptive
    -1.44
    glich
    -1.43
    dition
    -1.41
    lementary
    -1.39
    POSITIVE LOGITS
    church
    1.80
    bank
    1.79
    ifornia
    1.69
    shire
    1.69
    Pane
    1.64
    pole
    1.60
     needs
    1.52
    brit
    1.48
    izes
    1.47
    esque
    1.47
    Activations Density 0.061%

    No Known Activations