© 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. 8-RES_POST_32K-OAI
    11. 5086
    Prev
    Next
    INDEX
    Explanations

    references to large-scale events or groups, particularly in the context of violence or social issues

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    616
    +0.11
    0.5%
    445
    +0.10
    0.4%
    31
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.05
    616
    +0.10
    0.04
    638
    +0.10
    0.03
    Negative Logits
    mates
    -0.88
     mates
    -0.88
    mate
    -0.83
    poons
    -0.81
    men
    -0.77
    iour
    -0.77
    yssey
    -0.75
    ilda
    -0.74
    poon
    -0.73
    rious
    -0.72
    POSITIVE LOGITS
     mobilization
    0.98
     destruction
    0.92
     adoption
    0.86
     fabrication
    0.86
     deforestation
    0.83
     looting
    0.82
     doping
    0.81
     blackout
    0.80
     dismantling
    0.80
     disruption
    0.79
    Activations Density 0.282%

    No Known Activations