© 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. 29500
    Prev
    Next
    INDEX
    Explanations

    code-related terminology and structures

    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
    23
    +0.16
    0.9%
    189
    +0.12
    0.7%
    478
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.16
    0.11
    53
    +0.12
    0.10
    17
    +0.12
    0.06
    Negative Logits
    icum
    -1.81
    orial
    -1.69
    icals
    -1.59
    uable
    -1.59
    enne
    -1.54
    opsis
    -1.53
    ivir
    -1.50
    icul
    -1.49
    cit
    -1.48
    CoV
    -1.48
    POSITIVE LOGITS
    ¤
    1.83
     quar
    1.73
    ¿
    1.62
     awk
    1.62
    ķ
    1.60
    £
    1.60
    ¥
    1.58
    ľĵ
    1.56
     meantime
    1.54
    Ĥ
    1.53
    Activations Density 1.095%

    No Known Activations