© 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. 28881
    Prev
    Next
    INDEX
    Explanations

    commands related to output or echoing text in scripts

    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
    334
    +0.14
    0.8%
    53
    +0.12
    0.7%
    490
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    334
    +0.14
    0.02
    490
    +0.12
    0.01
    53
    +0.12
    0.02
    Negative Logits
    ĺ
    -2.18
    ĵ
    -2.15
    ij
    -2.06
    ĸ
    -1.89
    Ĥ
    -1.79
    ¤
    -1.75
    IJ
    -1.71
    ĭ
    -1.68
    AML
    -1.67
    ·¸
    -1.66
    POSITIVE LOGITS
    ulous
    1.60
    ging
    1.54
     choir
    1.43
    beat
    1.43
    acious
    1.42
    youtube
    1.39
     cardinal
    1.36
    cember
    1.35
    recorded
    1.34
    stained
    1.31
    Activations Density 0.092%

    No Known Activations