© 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. 2-RES-SM
    11. 31950
    Prev
    Next
    INDEX
    Explanations

    words related to professional roles and titles

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    253
    +0.13
    0.7%
    340
    +0.12
    0.7%
    419
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    340
    +0.13
    0.05
    253
    +0.12
    0.06
    448
    +0.12
    0.03
    Negative Logits
    inea
    -1.60
    *](#
    -1.56
     margin
    -1.55
     fracture
    -1.54
    ectin
    -1.53
    üssen
    -1.52
    ulic
    -1.48
    ÑĨиÑı
    -1.45
    ils
    -1.45
     limit
    -1.45
    POSITIVE LOGITS
     staff
    2.06
     retired
    1.98
     senior
    1.98
     supervised
    1.95
     chairman
    1.93
     assistants
    1.93
     executive
    1.93
     chairs
    1.90
     director
    1.89
     graduates
    1.87
    Activations Density 1.261%

    No Known Activations