© 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. 28739
    Prev
    Next
    INDEX
    Explanations

    occurrences of HTML or coding syntax elements

    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
    262
    +0.14
    0.8%
    110
    +0.12
    0.7%
    410
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    262
    +0.14
    0.05
    35
    +0.12
    0.03
    383
    +0.12
    0.03
    Negative Logits
    ħ
    -2.07
    onucle
    -2.01
    ical
    -1.67
    ĻĤ
    -1.65
    ©
    -1.57
    scape
    -1.56
    ¡
    -1.55
    apolis
    -1.55
    agers
    -1.53
    ¹
    -1.50
    POSITIVE LOGITS
    fully
    1.85
    producing
    1.53
    cession
    1.51
    priv
    1.50
     births
    1.47
    cloth
    1.47
     privilege
    1.35
     pitcher
    1.35
    <_
    1.35
    IGNED
    1.33
    Activations Density 0.133%

    No Known Activations