© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 10579
    Prev
    Next
    INDEX
    Explanations

    specific years and significant dates in sports and cultural contexts

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    29
    +0.12
    0.6%
    242
    +0.11
    0.6%
    253
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    29
    +0.12
    0.02
    226
    +0.11
    0.03
    145
    +0.11
    0.03
    Negative Logits
    iginally
    -1.93
    atile
    -1.90
    esty
    -1.72
    sein
    -1.67
    inity
    -1.65
    aries
    -1.60
    arily
    -1.58
    ldots
    -1.58
    urus
    -1.57
    dots
    -1.56
    POSITIVE LOGITS
    ↵↵↵
    3.29
    ↵  âĢĥ
    3.29
    č↵
    3.29
    <|outofrange|>
    3.29
    ↵
    3.29
    ↵↵
    3.29
    <|outofrange|>
    3.29
    3.29
    č↵
    3.29
    ↵↵
    3.29
    Activations Density 0.100%

    No Known Activations