© 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. 25710
    Prev
    Next
    INDEX
    Explanations

    terms related to psychiatric conditions and evaluations

    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
    156
    +0.23
    1.4%
    492
    +0.12
    0.7%
    228
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    492
    +0.23
    0.01
    361
    +0.12
    0.01
    71
    +0.11
    0.01
    Negative Logits
    oving
    -1.83
     primordial
    -1.62
    \!\!
    -1.54
     \:
    -1.52
     distant
    -1.48
    izi
    -1.48
     direct
    -1.47
     indirect
    -1.45
    sible
    -1.44
    \!\!\!
    -1.44
    POSITIVE LOGITS
     adviser
    1.84
     advisor
    1.68
    patients
    1.56
     analyst
    1.53
    caster
    1.53
    sheet
    1.51
    ische
    1.50
    scape
    1.49
    iatric
    1.49
    artment
    1.49
    Activations Density 0.056%

    No Known Activations