© 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. 4736
    Prev
    Next
    INDEX
    Explanations

    terms related to statistics and data analysis

    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
    373
    +0.16
    0.7%
    75
    +0.11
    0.5%
    295
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.16
    0.04
    659
    +0.11
    0.03
    350
    +0.10
    0.03
    Negative Logits
    smanship
    -0.65
     puzz
    -0.63
     lessons
    -0.62
    CHAT
    -0.60
     Borders
    -0.57
    ideos
    -0.57
     Signs
    -0.57
    )].
    -0.55
     Plane
    -0.55
     contingency
    -0.55
    POSITIVE LOGITS
    atta
    0.76
    onde
    0.73
    ua
    0.72
    aug
    0.72
    asma
    0.71
    oeuv
    0.68
    ange
    0.67
    ennis
    0.67
    oute
    0.65
    oshi
    0.65
    Activations Density 0.204%

    No Known Activations