© 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. 1-RES-SM
    11. 24268
    Prev
    Next
    INDEX
    Explanations

    words related to media, particularly anime and manga

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    247
    +0.14
    0.8%
    250
    +0.13
    0.7%
    466
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    178
    +0.14
    0.01
    272
    +0.13
    0.01
    399
    +0.12
    0.01
    Negative Logits
    ĻĤ
    -2.47
    ĥ
    -2.37
    Ģ
    -2.29
    Īĺ
    -2.26
    ĵ
    -2.18
    º
    -2.07
    Ħ
    -1.94
    Ĥ
    -1.89
    ķ
    -1.89
    ĺ
    -1.87
    POSITIVE LOGITS
    aurus
    2.13
    othe
    2.00
    enda
    1.96
     relate
    1.76
    rett
    1.73
    endi
    1.66
    ksen
    1.64
    velt
    1.63
    ères
    1.61
    cias
    1.60
    Activations Density 0.118%

    No Known Activations