© 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. 2-RES-SM
    11. 12381
    Prev
    Next
    INDEX
    Explanations

    references to feelings of disrespect or lack of courtesy

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    429
    +0.12
    0.7%
    332
    +0.12
    0.7%
    295
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    38
    +0.12
    0.00
    166
    +0.12
    0.00
    326
    +0.12
    0.00
    Negative Logits
    Ī
    -1.76
    ľĵ
    -1.73
    ĸ
    -1.72
    Ĩ
    -1.67
    <|outofrange|>
    -1.58
    ↵
    -1.58
    ↵
    -1.58
    ↵
    -1.58
    ↵
    -1.58
     ↵
    -1.58
    POSITIVE LOGITS
    >$
    1.65
    >&
    1.60
    ules
    1.44
    uous
    1.43
     largest
    1.43
     consoles
    1.39
    aries
    1.39
    arly
    1.37
     Xbox
    1.32
    eded
    1.32
    Activations Density 0.000%

    No Known Activations