© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11357
    Prev
    Next
    INDEX
    Explanations

    references to music charts and sales performance

    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
    341
    +0.13
    0.7%
    319
    +0.12
    0.7%
    10
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    341
    +0.13
    0.09
    319
    +0.12
    0.05
    511
    +0.11
    0.03
    Negative Logits
    ↵
    -2.68
    ↵↵
    -2.68
    -2.68
     ↵
    -2.68
    ↵
    -2.68
    ↵↵
    -2.68
    ↵↵↵
    -2.68
    ↵
    -2.68
    ↵
    -2.68
    <|outofrange|>
    -2.68
    POSITIVE LOGITS
     premiere
    1.92
     rankings
    1.90
     Awards
    1.86
     audience
    1.82
     ratings
    1.82
     Players
    1.74
     auction
    1.73
     ranks
    1.72
     awards
    1.69
     scene
    1.69
    Activations Density 1.083%

    No Known Activations