© 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. 26438
    Prev
    Next
    INDEX
    Explanations

    reports or statements from individuals

    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
    +0.19
    1.1%
    404
    +0.13
    0.7%
    244
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    432
    +0.19
    0.06
    11
    +0.13
    0.05
    474
    +0.12
    0.05
    Negative Logits
    pective
    -1.80
    !)
    -1.79
    ”)
    -1.78
    ?”
    -1.78
    !(
    -1.78
    ”).
    -1.73
    »¿
    -1.70
    ”?
    -1.70
    ?)
    -1.69
     influences
    -1.69
    POSITIVE LOGITS
     reporters
    1.47
     faint
    1.43
    inx
    1.41
    GN
    1.41
    uously
    1.40
    unting
    1.40
    ilst
    1.40
    anches
    1.39
    aterally
    1.39
    ching
    1.36
    Activations Density 0.366%

    No Known Activations