© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 4-RES-SM
    6. 14269
    Prev
    Next
    INDEX
    Explanations

    references to "cast" in various contexts, particularly related to performing arts or film

    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
    375
    +0.13
    0.7%
    212
    +0.10
    0.6%
    417
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    218
    +0.13
    0.02
    212
    +0.10
    0.02
    386
    +0.10
    0.00
    Negative Logits
    pie
    -1.71
    unnumbered
    -1.67
    ware
    -1.60
    ĻĤ
    -1.54
    cip
    -1.48
     conservation
    -1.45
    NAL
    -1.44
     University
    -1.40
     oxidase
    -1.39
    wards
    -1.32
    POSITIVE LOGITS
    ration
    2.65
    aways
    2.65
    igating
    2.54
    rated
    2.52
    rating
    2.47
    igation
    2.26
    igated
    2.24
    illo
    2.23
    les
    2.14
    away
    2.10
    Activations Density 0.272%

    No Known Activations