© 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. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 27093
    Prev
    Next
    INDEX
    Explanations

    negative sentiments or adverse situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    373
    +0.11
    0.5%
    220
    +0.10
    0.5%
    82
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    766
    +0.11
    0.01
    537
    +0.10
    0.01
    134
    +0.10
    0.01
    Negative Logits
    come
    -0.78
     Ago
    -0.76
    dylib
    -0.74
    enth
    -0.73
    spir
    -0.73
    gaard
    -0.73
    thood
    -0.72
    schild
    -0.71
    riott
    -0.70
    sea
    -0.67
    POSITIVE LOGITS
     masked
    0.62
     unab
    0.61
    Paul
    0.61
    Brian
    0.60
     Brian
    0.60
    Rachel
    0.60
    Shot
    0.58
     transcription
    0.58
    GoldMagikarp
    0.58
    ozyg
    0.57
    Activations Density 0.056%

    No Known Activations