© 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. 4955
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals, particularly by name

    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
    604
    +0.15
    0.7%
    407
    +0.12
    0.5%
    36
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.15
    0.07
    735
    +0.12
    0.04
    176
    +0.11
    0.03
    Negative Logits
    tons
    -0.73
     ultras
    -0.68
     Templar
    -0.63
     Totem
    -0.63
     Gothic
    -0.62
    chance
    -0.59
     Houses
    -0.59
    checked
    -0.58
     hint
    -0.58
     penetrating
    -0.58
    POSITIVE LOGITS
    utton
    0.88
    yss
    0.87
    ulla
    0.86
    affer
    0.85
    ynes
    0.83
    iggs
    0.83
    ijah
    0.81
    owell
    0.81
    uchin
    0.78
    angelo
    0.77
    Activations Density 0.149%

    No Known Activations