© 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. 2-RES-SM
    11. 28546
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific characters or sequences within text

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    90
    +0.13
    0.7%
    261
    +0.12
    0.7%
    427
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    90
    +0.13
    0.04
    370
    +0.12
    0.04
    133
    +0.11
    0.03
    Negative Logits
    s
    -1.78
    mers
    -1.78
    )](
    -1.59
    Inflater
    -1.54
    .’”
    -1.53
    ).](
    -1.48
     distribution
    -1.45
    fax
    -1.45
    .[]{
    -1.44
    '>
    -1.44
    POSITIVE LOGITS
    ĨĴ
    2.04
     slog
    1.79
    ±
    1.78
    ĻĤ
    1.71
    ·
    1.67
    į
    1.65
    ĭ
    1.61
    Į
    1.53
    TRODUCTION
    1.52
    ¿½
    1.49
    Activations Density 0.200%

    No Known Activations