© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 29990
    Prev
    Next
    INDEX
    Explanations

    requests for user information and identity verification in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.19
    1.1%
    98
    +0.14
    0.8%
    292
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    237
    +0.19
    0.12
    98
    +0.14
    -0.03
    293
    +0.10
    0.10
    Negative Logits
    ↵            ↵
    -2.30
    č↵
    -2.30
    ↵
    -2.30
    ↵
    -2.30
    ↵↵
    -2.30
    -2.30
    -2.30
    <|outofrange|>
    -2.30
    ↵
    -2.30
    -2.30
    POSITIVE LOGITS
    jee
    1.88
    ();
    1.51
    ():
    1.48
     ();
    1.43
    kar
    1.41
     Brexit
    1.40
    hol
    1.39
    val
    1.38
     bog
    1.36
    uka
    1.33
    Activations Density 2.198%

    No Known Activations