© 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. 28199
    Prev
    Next
    INDEX
    Explanations

    the word "ill" 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/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
    81
    +0.16
    0.9%
    177
    +0.12
    0.7%
    16
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    101
    +0.16
    0.02
    81
    +0.12
    0.02
    452
    +0.11
    0.02
    Negative Logits
    ¦
    -1.99
    Ĥ
    -1.97
    °
    -1.84
    Ĺ
    -1.82
    ĸ´
    -1.75
    ³
    -1.73
    ationally
    -1.72
    ¾
    -1.71
    ±
    -1.71
     peace
    -1.68
    POSITIVE LOGITS
    iere
    2.16
    ouin
    2.12
    ustration
    1.96
    ermo
    1.90
    ière
    1.88
    ée
    1.85
    ustr
    1.83
    ache
    1.77
    ie
    1.76
    azzo
    1.75
    Activations Density 0.102%

    No Known Activations