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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5486
    Prev
    Next
    INDEX
    Explanations

    references to the term "Versailles."

    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
    68
    +0.10
    0.5%
    373
    +0.10
    0.4%
    581
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.02
    404
    +0.10
    0.01
    124
    +0.09
    0.01
    Negative Logits
    butt
    -0.77
    OPLE
    -0.72
    ãĥ£
    -0.69
    MER
    -0.66
    pt
    -0.65
     seeker
    -0.65
    ISSION
    -0.65
     conversion
    -0.63
    dding
    -0.61
    mun
    -0.59
    POSITIVE LOGITS
    atile
    1.68
    atility
    1.55
    ions
    1.04
    aries
    1.01
    alis
    0.99
    ationally
    0.97
    erver
    0.93
    ilage
    0.92
    ational
    0.92
    hap
    0.91
    Activations Density 0.077%

    No Known Activations