© 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. 1-RES-SM
    11. 27535
    Prev
    Next
    INDEX
    Explanations

    instances of the word "consists" or its variations, indicating descriptions of composition or structure

    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
    376
    +0.16
    0.9%
    23
    +0.13
    0.8%
    444
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    367
    +0.16
    0.02
    68
    +0.13
    0.02
    444
    +0.13
    0.02
    Negative Logits
    oses
    -1.53
    legal
    -1.52
     career
    -1.43
     tiempo
    -1.42
    ables
    -1.41
    ugu
    -1.39
    chron
    -1.39
     sale
    -1.39
    makers
    -1.39
     Contest
    -1.37
    POSITIVE LOGITS
    ishly
    1.70
    ially
    1.69
    inese
    1.69
    kered
    1.52
    lining
    1.50
    enza
    1.49
    yline
    1.46
    acious
    1.46
    ographically
    1.39
    ridges
    1.38
    Activations Density 0.063%

    No Known Activations