© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 15096
    Prev
    Next
    INDEX
    Explanations

    elements related to character names and literary references in narratives

    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
    21
    +0.18
    1.0%
    156
    +0.15
    0.9%
    25
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    130
    +0.18
    0.10
    410
    +0.15
    0.08
    425
    +0.14
    0.11
    Negative Logits
    <|outofrange|>
    -9.35
    -9.35
    ↵↵
    -9.35
    <|outofrange|>
    -9.35
    ↵↵
    -9.35
    -9.35
    -9.35
    <|outofrange|>
    -9.35
    <|padding|>
    -9.35
    -9.35
    POSITIVE LOGITS
     Productions
    2.70
     Films
    2.63
     trilogy
    2.56
     premiered
    2.48
     starring
    2.43
     Comics
    2.33
     soundtrack
    2.26
     Studios
    2.11
     Theater
    2.11
     Theatre
    2.08
    Activations Density 1.558%

    No Known Activations