© 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. 24307
    Prev
    Next
    INDEX
    Explanations

    terms related to the severity and impact of various conditions or actions

    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
    +0.15
    0.9%
    352
    +0.14
    0.8%
    301
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    385
    +0.15
    0.01
    301
    +0.14
    0.01
    232
    +0.09
    0.01
    Negative Logits
    emale
    -1.73
    blogger
    -1.57
     parte
    -1.55
     shame
    -1.52
    ubicin
    -1.52
     lots
    -1.51
     her
    -1.48
     wonder
    -1.43
    ece
    -1.43
     hers
    -1.42
    POSITIVE LOGITS
    ļ
    2.07
    ¯
    1.87
    ally
    1.80
    Ł
    1.79
    ismatic
    1.79
    ī
    1.74
    chart
    1.73
    ĩ
    1.72
    ality
    1.72
    Ĩ
    1.71
    Activations Density 0.060%

    No Known Activations