© 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. 10714
    Prev
    Next
    INDEX
    Explanations

    references to accessibility and assistance for individuals with disabilities

    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
    21
    +0.17
    1.0%
    78
    +0.13
    0.7%
    126
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.17
    -0.00
    255
    +0.13
    -0.00
    397
    +0.11
    0.02
    Negative Logits
    ”.
    -2.22
    ”).
    -2.00
    ”,
    -1.93
    *]{}.
    -1.89
    ”),
    -1.86
    \]).
    -1.83
    .^\[[@
    -1.81
    .“
    -1.79
    ”:
    -1.79
    \_
    -1.76
    POSITIVE LOGITS
    1.64
    à¸Ĺ
    1.61
    1.61
    1.61
    à¹Ī
    1.59
    1.58
     -----
    1.56
    า
    1.55
     messages
    1.55
    1.54
    Activations Density 0.111%

    No Known Activations