© 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. 29457
    Prev
    Next
    INDEX
    Explanations

    terms related to connectors and their specifications

    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
    486
    +0.14
    0.8%
    443
    +0.12
    0.7%
    278
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    278
    +0.14
    0.02
    194
    +0.12
    0.02
    43
    +0.12
    0.02
    Negative Logits
     relentless
    -1.66
     least
    -1.62
     worst
    -1.56
     weekly
    -1.54
     um
    -1.53
     random
    -1.52
     fierce
    -1.52
     cual
    -1.48
     successive
    -1.48
     mortal
    -1.47
    POSITIVE LOGITS
    osity
    2.11
    amycin
    1.89
    ilage
    1.82
    anium
    1.69
    sten
    1.68
    imab
    1.64
    amic
    1.59
    imet
    1.55
    ulence
    1.54
    "}](#
    1.52
    Activations Density 0.121%

    No Known Activations