© 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. 25930
    Prev
    Next
    INDEX
    Explanations

    specific references to genes or genetic data

    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
    47
    +0.17
    1.0%
    134
    +0.11
    0.7%
    306
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.17
    0.04
    12
    +0.11
    0.03
    508
    +0.11
    0.04
    Negative Logits
     deaf
    -1.76
     kidding
    -1.68
     unemploy
    -1.66
     lazy
    -1.62
     fucking
    -1.59
     calm
    -1.58
     Deaf
    -1.56
     unemployed
    -1.56
     dont
    -1.56
     ship
    -1.54
    POSITIVE LOGITS
    iral
    1.79
    »¿
    1.75
    ade
    1.74
    bars
    1.71
    abil
    1.71
     ([@
    1.70
    ^[@
    1.68
    abla
    1.65
    vist
    1.65
     provides
    1.63
    Activations Density 0.340%

    No Known Activations