© 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. 5421
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Johnson."

    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
    162
    +0.12
    0.5%
    339
    +0.12
    0.5%
    376
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.02
    502
    +0.12
    0.01
    162
    +0.11
    0.01
    Negative Logits
    ãĥį
    -0.77
    lessly
    -0.75
    ter
    -0.75
    ãĤ·ãĥ£
    -0.74
    acters
    -0.72
    apter
    -0.71
    ãĥ¡
    -0.68
    ters
    -0.67
    ine
    -0.67
    neau
    -0.67
    POSITIVE LOGITS
    ety
    0.91
    ente
    0.81
    arov
    0.78
    hovah
    0.73
    alsa
    0.71
    ĺ
    0.68
     Virtue
    0.68
    undo
    0.68
    eter
    0.68
    erness
    0.67
    Activations Density 0.060%

    No Known Activations