© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 11166
    Prev
    Next
    INDEX
    Explanations

    data types and structure definitions in programming

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    148
    +0.14
    0.7%
    204
    +0.12
    0.7%
    108
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.14
    0.04
    204
    +0.12
    0.04
    213
    +0.11
    0.04
    Negative Logits
    ¿½
    -3.31
    ĸ
    -2.91
    ¸
    -2.89
    ĻĤ
    -2.81
    Ħ
    -2.81
    »¿
    -2.75
    ´
    -2.74
    Ĥ¬
    -2.69
    ·¸
    -2.67
    ĨĴ
    -2.67
    POSITIVE LOGITS
    uitively
    2.50
    uitive
    2.44
    ptr
    1.94
    uments
    1.87
    64
    1.84
    Value
    1.83
    argin
    1.80
    [])
    1.78
    ellig
    1.75
    __(
    1.73
    Activations Density 0.253%

    No Known Activations