© 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. 24207
    Prev
    Next
    INDEX
    Explanations

    expressions of apology or regret

    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
    365
    +0.14
    0.8%
    505
    +0.13
    0.7%
    410
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    505
    +0.14
    0.03
    394
    +0.13
    0.03
    503
    +0.12
    0.02
    Negative Logits
    ħ
    -1.62
    works
    -1.56
    ores
    -1.54
    eten
    -1.52
     Studies
    -1.49
    Illustration
    -1.48
    /-/
    -1.45
    ene
    -1.40
    odynamics
    -1.39
    ĥ½
    -1.39
    POSITIVE LOGITS
    giving
    1.62
     tz
    1.51
     mistake
    1.50
     little
    1.48
     excuse
    1.48
     old
    1.44
    fully
    1.44
     distraction
    1.44
     surprise
    1.42
    ler
    1.41
    Activations Density 0.223%

    No Known Activations