© 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. 28566
    Prev
    Next
    INDEX
    Explanations

    terms related to acute toxicity and lab testing procedures

    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
    156
    +0.31
    1.8%
    111
    +0.15
    0.9%
    17
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.31
    0.34
    271
    +0.15
    0.17
    156
    +0.13
    0.16
    Negative Logits
    isenberg
    -1.52
    ogen
    -1.46
    schild
    -1.43
    ynman
    -1.42
    fit
    -1.39
    [@
    -1.34
    об
    -1.32
    ffff
    -1.29
    ollo
    -1.27
     https
    -1.27
    POSITIVE LOGITS
    tered
    1.58
    spir
    1.58
    inous
    1.55
    join
    1.52
    aped
    1.46
     trafficking
    1.41
    ially
    1.40
     midst
    1.40
     hearts
    1.36
     forfeiture
    1.34
    Activations Density 0.457%

    No Known Activations