© 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. 4-RES-SM
    11. 9668
    Prev
    Next
    INDEX
    Explanations

    concepts related to psychological research and behavioral science

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    108
    +0.14
    0.8%
    305
    +0.12
    0.7%
    110
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    124
    +0.14
    0.07
    234
    +0.12
    0.06
    401
    +0.12
    0.04
    Negative Logits
    č↵
    -6.91
          ↵
    -6.91
    -6.91
    -6.91
    <|outofrange|>
    -6.91
    ↵
    -6.91
    <|outofrange|>
    -6.91
    ↵
    -6.91
    ↵
    -6.91
    -6.91
    POSITIVE LOGITS
     were
    2.53
     respectively
    2.45
    were
    1.98
     remain
    1.75
     thereof
    1.68
    taient
    1.59
     ensued
    1.58
     suggest
    1.57
    }$\
    1.57
     constitute
    1.56
    Activations Density 1.512%

    No Known Activations