© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1-RES-SM
    11. 27189
    Prev
    Next
    INDEX
    Explanations

    specific punctuation and formatting patterns in 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/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
    391
    +0.13
    0.7%
    384
    +0.13
    0.7%
    168
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.13
    0.00
    493
    +0.13
    0.00
    380
    +0.12
    0.00
    Negative Logits
    ®
    -2.03
    Ľ
    -2.02
    Ĭ
    -1.93
    Ĩ
    -1.83
    Ĥ¬
    -1.77
    ĭ
    -1.73
    »¿
    -1.73
    »
    -1.68
    ¥
    -1.67
    ¢
    -1.66
    POSITIVE LOGITS
    lies
    1.62
    inois
    1.57
    leen
    1.56
    theless
    1.53
     attention
    1.47
    lene
    1.44
    cé
    1.44
    ly
    1.43
    olip
    1.42
    othy
    1.40
    Activations Density 0.001%

    No Known Activations