© 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. 8958
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and procedural terminology

    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
    156
    +0.17
    1.0%
    78
    +0.14
    0.8%
    348
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    168
    +0.17
    0.09
    410
    +0.14
    0.07
    332
    +0.13
    0.08
    Negative Logits
     ^[@
    -1.66
     favour
    -1.63
     etc
    -1.60
    imization
    -1.58
    tons
    -1.51
    ALSE
    -1.47
    topic
    -1.44
    .^[@
    -1.39
    aft
    -1.39
    )^[@
    -1.38
    POSITIVE LOGITS
    Ī
    2.58
    ’
    2.55
    ī
    2.48
    Ĩ
    2.37
    ↵Č
    2.35
     (“
    2.29
    ľĵ
    2.26
    âĢŁ
    2.17
    ı
    2.16
    »¿
    2.15
    Activations Density 0.707%

    No Known Activations