© 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. 29296
    Prev
    Next
    INDEX
    Explanations

    instances where attention to a specific issue or topic is emphasized

    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
    38
    +0.18
    1.1%
    466
    +0.16
    0.9%
    314
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    38
    +0.18
    0.04
    287
    +0.16
    0.03
    314
    +0.15
    0.03
    Negative Logits
    nen
    -1.85
     dia
    -1.53
    nis
    -1.53
    stitute
    -1.50
    nia
    -1.50
    eration
    -1.49
    Ľ
    -1.45
    solid
    -1.44
    ?’
    -1.42
    ubicin
    -1.42
    POSITIVE LOGITS
    pieces
    1.86
    piece
    1.64
    ily
    1.63
     blur
    1.60
    al
    1.59
     grabbing
    1.51
     alerts
    1.51
    cards
    1.50
    lessly
    1.44
    ive
    1.44
    Activations Density 0.113%

    No Known Activations