© 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. 24494
    Prev
    Next
    INDEX
    Explanations

    phrases indicating approximation or estimation

    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
    478
    +0.15
    0.9%
    69
    +0.14
    0.8%
    52
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    52
    +0.15
    0.05
    102
    +0.14
    0.04
    364
    +0.14
    0.05
    Negative Logits
    nger
    -1.66
    elijk
    -1.63
    istics
    -1.61
     upon
    -1.58
    arity
    -1.58
    over
    -1.55
    INGS
    -1.50
    ette
    -1.49
    bron
    -1.47
    LEY
    -1.45
    POSITIVE LOGITS
    ĵ
    2.29
    ł
    2.21
    ¿½
    2.14
    Ń
    2.13
    ¹
    2.11
    ľĵ
    2.04
    ¨
    2.04
    ¶
    1.99
    ³
    1.95
    ²
    1.93
    Activations Density 0.145%

    No Known Activations