© 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. 4-RES-SM
    11. 11785
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation or special characters in a 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/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
    271
    +0.14
    0.8%
    147
    +0.13
    0.7%
    422
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    461
    +0.14
    0.03
    129
    +0.13
    0.02
    17
    +0.12
    0.02
    Negative Logits
     toll
    -1.50
    etes
    -1.48
    pes
    -1.44
     healthy
    -1.42
     Industries
    -1.39
    ?",
    -1.37
    ]\];
    -1.35
    ]\],
    -1.35
    eston
    -1.32
    ier
    -1.30
    POSITIVE LOGITS
    ľ
    3.68
    ¼
    3.47
    Ķ
    3.33
    Ĺ
    3.33
    ļ
    3.33
    ľĵ
    3.29
    ŀ
    3.25
    ĺ
    3.24
    Ĥ
    3.23
    ĥ½
    3.17
    Activations Density 0.307%

    No Known Activations