© 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. 13114
    Prev
    Next
    INDEX
    Explanations

    texts that discuss narratives and storytelling

    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
    306
    +0.15
    0.8%
    375
    +0.13
    0.7%
    228
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.15
    0.03
    375
    +0.13
    0.03
    38
    +0.13
    0.04
    Negative Logits
    ¥
    -2.37
    §
    -2.35
    ħ
    -2.28
    ·¸
    -2.26
    ¯
    -2.23
    ł
    -2.23
    ĸ´
    -2.22
    ½
    -2.21
    ĥ½
    -2.19
    ĸ
    -2.16
    POSITIVE LOGITS
    lines
    3.15
    telling
    2.83
    boards
    2.65
    line
    2.65
    book
    2.62
    board
    2.49
     unfold
    2.45
     narr
    2.28
    books
    2.13
     line
    2.11
    Activations Density 0.555%

    No Known Activations