© 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. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 8873
    Prev
    Next
    INDEX
    Explanations

    phrases indicating provocation or sparked responses in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    512
    +0.10
    0.4%
    463
    +0.10
    0.4%
    671
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.10
    0.10
    362
    +0.10
    0.07
    159
    +0.09
    0.05
    Negative Logits
    station
    -0.69
    osponsors
    -0.64
    é¾įå
    -0.64
     sake
    -0.62
     coefficients
    -0.61
     survived
    -0.61
    omorphic
    -0.60
     deceased
    -0.59
    raped
    -0.59
     embodiments
    -0.58
    POSITIVE LOGITS
     outcry
    1.09
     backlash
    1.08
     uproar
    0.99
     rethink
    0.99
     frenzy
    0.98
     flurry
    0.98
     outburst
    0.97
     cascade
    0.96
     debate
    0.94
     eruption
    0.91
    Activations Density 0.507%

    No Known Activations