© 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. 26546
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "be"

    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
    478
    +0.16
    0.9%
    419
    +0.12
    0.7%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    179
    +0.16
    0.02
    419
    +0.12
    0.02
    281
    +0.12
    0.02
    Negative Logits
    Ł
    -2.56
    ij
    -2.44
    ¢
    -2.38
    ©
    -2.37
    £
    -2.36
    İ
    -2.33
    ħ
    -2.30
    Ľ
    -2.27
    Ļ
    -2.21
    Ī
    -2.17
    POSITIVE LOGITS
    aucoup
    1.65
    wards
    1.59
    zier
    1.55
     wk
    1.52
     annually
    1.49
    gets
    1.49
     grading
    1.46
     graded
    1.45
     Syrian
    1.34
     grateful
    1.34
    Activations Density 0.075%

    No Known Activations