© 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. 26431
    Prev
    Next
    INDEX
    Explanations

    structures related to web form components

    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
    163
    +0.12
    0.7%
    386
    +0.10
    0.6%
    23
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    466
    +0.12
    0.03
    491
    +0.10
    0.04
    21
    +0.10
    0.03
    Negative Logits
     ever
    -1.76
    nier
    -1.67
    ocur
    -1.50
     itself
    -1.46
    culus
    -1.46
     sometime
    -1.44
    ?)
    -1.42
    ensis
    -1.41
    ero
    -1.40
     himself
    -1.40
    POSITIVE LOGITS
    ¿½
    2.82
    ¦
    2.79
    ľĵ
    2.66
    Į
    2.63
    ©
    2.55
    ¿
    2.50
    ĥ½
    2.45
    ľ
    2.36
    Īĺ
    2.30
    ³
    2.28
    Activations Density 0.418%

    No Known Activations