© 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. 13536
    Prev
    Next
    INDEX
    Explanations

    actions or activities that involve performing tasks or behaviors

    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
    318
    +0.16
    0.9%
    343
    +0.11
    0.6%
    110
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    318
    +0.16
    0.02
    66
    +0.11
    0.03
    343
    +0.11
    0.03
    Negative Logits
    ://
    -1.70
     discussion
    -1.64
    oses
    -1.62
    blogger
    -1.55
    dale
    -1.52
    ·¸
    -1.50
    µ
    -1.43
     discussions
    -1.42
     BGCOLOR
    -1.41
     fois
    -1.41
    POSITIVE LOGITS
    uated
    2.91
    uating
    2.81
    uary
    2.80
    uate
    2.73
    ivities
    2.60
    inic
    2.45
    uation
    2.42
    igraphy
    2.39
    ivated
    2.23
    uates
    1.96
    Activations Density 0.171%

    No Known Activations