© 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. 12840
    Prev
    Next
    INDEX
    Explanations

    command-related language, particularly in the context of programming or operating systems

    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
    307
    +0.21
    1.2%
    306
    +0.14
    0.8%
    172
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    219
    +0.21
    0.03
    17
    +0.14
    0.01
    441
    +0.12
    0.00
    Negative Logits
    ovember
    -1.63
    idays
    -1.56
    agland
    -1.55
    oyl
    -1.55
    abad
    -1.43
    Ĭ
    -1.42
    оÐ
    -1.38
     studies
    -1.34
    »¿
    -1.34
     humidity
    -1.34
    POSITIVE LOGITS
    line
    2.74
     line
    2.41
     prompt
    2.40
    eered
    1.98
    ments
    1.87
    lines
    1.87
     manual
    1.86
     cmd
    1.85
     executed
    1.80
     console
    1.79
    Activations Density 0.191%

    No Known Activations