© 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. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 28780
    Prev
    Next
    INDEX
    Explanations

    mentions of government agencies or entities involved in enforcement or regulation

    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
    1
    +0.10
    0.4%
    354
    +0.09
    0.4%
    475
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.10
    -0.01
    284
    +0.09
    0.04
    374
    +0.09
    -0.02
    Negative Logits
     Savings
    -0.62
    pread
    -0.59
    ailability
    -0.57
    lap
    -0.56
     cov
    -0.56
    ngth
    -0.56
     Glac
    -0.54
    aters
    -0.54
     bathrooms
    -0.54
     +/-
    -0.54
    POSITIVE LOGITS
    yt
    0.74
    inson
    0.73
    oned
    0.68
    oning
    0.67
    itus
    0.67
    vez
    0.67
    onite
    0.66
    io
    0.65
    ion
    0.65
    ees
    0.65
    Activations Density 0.826%

    No Known Activations