© 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. 25068
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "pp."

    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
    317
    +0.16
    0.9%
    2
    +0.12
    0.7%
    502
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    317
    +0.16
    0.02
    92
    +0.12
    0.01
    2
    +0.11
    0.02
    Negative Logits
    ¼
    -2.86
    ·¸
    -2.63
    °
    -2.31
    Īĺ
    -2.29
    ľĵ
    -2.25
    ĻĤ
    -2.23
    ½
    -2.11
    Ļ
    -1.93
    ľ
    -1.91
    µ
    -1.90
    POSITIVE LOGITS
    recht
    2.42
    endor
    2.15
    ings
    1.86
    lication
    1.83
    bian
    1.83
    ungs
    1.79
    len
    1.79
    onte
    1.78
    lications
    1.77
    num
    1.75
    Activations Density 0.074%

    No Known Activations