© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4665
    Prev
    Next
    INDEX
    Explanations

    references to historical events and figures related to the Civil War and slavery

    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
    339
    +0.12
    0.5%
    294
    +0.11
    0.5%
    496
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.05
    659
    +0.11
    0.03
    99
    +0.11
    0.02
    Negative Logits
    OSH
    -0.80
    cases
    -0.73
    eger
    -0.71
    eworthy
    -0.71
    anyahu
    -0.70
    OSP
    -0.69
    gging
    -0.66
    kok
    -0.64
    ophone
    -0.63
    wig
    -0.63
    POSITIVE LOGITS
     Confederacy
    0.96
    ipation
    0.89
     secession
    0.79
     1862
    0.77
    ribute
    0.76
     Confederate
    0.75
     1861
    0.74
     1863
    0.73
     Flag
    0.73
     plantation
    0.72
    Activations Density 0.234%

    No Known Activations