© 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. 27892
    Prev
    Next
    INDEX
    Explanations

    structured programming elements and data types

    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
    135
    +0.15
    0.9%
    369
    +0.12
    0.7%
    436
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    176
    +0.15
    0.19
    135
    +0.12
    0.16
    108
    +0.12
    0.16
    Negative Logits
     Profess
    -1.61
     attorneys
    -1.58
    /~
    -1.54
     instructors
    -1.50
     professors
    -1.44
     psychologists
    -1.41
    ki
    -1.40
     professions
    -1.37
     lawyers
    -1.37
    ableness
    -1.34
    POSITIVE LOGITS
    burn
    1.59
    goto
    1.58
     result
    1.57
    ital
    1.49
    ressor
    1.49
    inho
    1.48
    iate
    1.47
    result
    1.46
    ifice
    1.43
    izza
    1.43
    Activations Density 8.359%

    No Known Activations