© 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. 26649
    Prev
    Next
    INDEX
    Explanations

    the word "that" in various contexts

    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
    23
    +0.25
    1.5%
    478
    +0.16
    0.9%
    209
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.25
    0.04
    466
    +0.16
    0.03
    419
    +0.13
    0.03
    Negative Logits
    ”?
    -1.85
    ”
    -1.70
    ”:
    -1.62
    ”;
    -1.62
    bod
    -1.55
    ec
    -1.54
    ?”
    -1.54
    }</
    -1.54
    )</
    -1.49
    films
    -1.49
    POSITIVE LOGITS
    ĥ½
    2.02
    1.86
    ↵
    1.86
     ↵
    1.86
    1.86
    1.86
    <|outofrange|>
    1.86
    1.86
    <|outofrange|>
    1.86
    ↵Č
    1.86
    Activations Density 0.236%

    No Known Activations