© 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 EvalsExportsinterp-engineNEWAPI 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. 28250
    Prev
    Next
    INDEX
    Explanations

    instances of the word "as" used 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
    +0.20
    1.1%
    424
    +0.19
    1.1%
    478
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    424
    +0.20
    0.09
    502
    +0.19
    0.06
    41
    +0.14
    0.04
    Negative Logits
    itud
    -1.98
    aries
    -1.78
    arget
    -1.71
    vable
    -1.63
    ible
    -1.61
    emic
    -1.58
    UIT
    -1.54
    erent
    -1.53
    rained
    -1.53
    ered
    -1.47
    POSITIVE LOGITS
    ¶
    3.60
    ²
    3.32
    ī
    3.19
    ↵
    3.12
    č↵
    3.12
    č↵
    3.12
              ↵
    3.12
    <|outofrange|>
    3.12
    ↵
    3.12
    3.12
    Activations Density 0.181%

    No Known Activations