© 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 EvalsExportsAPI 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. 26266
    Prev
    Next
    INDEX
    Explanations

    programming language imports and dependencies

    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
    290
    +0.14
    0.8%
    12
    +0.12
    0.7%
    182
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    290
    +0.14
    0.02
    12
    +0.12
    0.02
    235
    +0.10
    0.02
    Negative Logits
    à±ģ
    -1.81
    asian
    -1.78
    unnumbered
    -1.69
    coins
    -1.62
    cus
    -1.62
    dez
    -1.61
    à°¿
    -1.59
    HPP
    -1.58
    substack
    -1.57
    sic
    -1.57
    POSITIVE LOGITS
    ('./
    1.83
     '../
    1.68
    ://
    1.67
     recalls
    1.51
    quilibrium
    1.50
     manual
    1.49
     './
    1.47
    eless
    1.42
     comprom
    1.41
     vary
    1.39
    Activations Density 0.091%

    No Known Activations