© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 14768
    Prev
    Next
    INDEX
    Explanations

    references to wild animals or wildness in various 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
    410
    +0.16
    0.9%
    345
    +0.12
    0.6%
    186
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    82
    +0.16
    0.02
    326
    +0.12
    0.02
    410
    +0.11
    0.02
    Negative Logits
    ect
    -1.64
    unnumbered
    -1.57
    :`
    -1.56
     thereof
    -1.54
    aser
    -1.37
     further
    -1.36
     effective
    -1.35
    OUBLE
    -1.35
     itself
    -1.34
    uez
    -1.33
    POSITIVE LOGITS
    Ĵ
    2.96
    fires
    2.93
    fire
    2.75
    ¼
    2.63
    Ģ
    2.61
    £
    2.52
    ij
    2.48
    ł
    2.42
    »
    2.40
    Ļ
    2.38
    Activations Density 0.245%

    No Known Activations