© 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. 26053
    Prev
    Next
    INDEX
    Explanations

    terms related to associations between various health conditions or factors

    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
    148
    +0.15
    0.8%
    315
    +0.13
    0.7%
    283
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.15
    0.02
    315
    +0.13
    0.02
    148
    +0.13
    0.01
    Negative Logits
    llo
    -1.92
    aser
    -1.60
    asers
    -1.59
    ilos
    -1.58
    genstein
    -1.57
    uncture
    -1.44
    rives
    -1.39
    ço
    -1.38
    ubicin
    -1.34
    icul
    -1.33
    POSITIVE LOGITS
     sexes
    1.83
     with
    1.76
     diseases
    1.73
     subgroup
    1.58
     subgroups
    1.56
     degradation
    1.55
    rÃŃ
    1.54
     groups
    1.47
    unnumbered
    1.46
     fields
    1.43
    Activations Density 0.067%

    No Known Activations