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

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES_POST_32K-OAI
    11. 30868
    Prev
    Next
    INDEX
    Explanations

    terms related to groups or associations of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    578
    +0.11
    0.5%
    537
    +0.10
    0.5%
    657
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.11
    0.04
    224
    +0.10
    0.05
    537
    +0.10
    0.05
    Negative Logits
    worms
    -0.76
    ctors
    -0.68
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.68
    holders
    -0.66
    ographers
    -0.65
    ASED
    -0.65
    oÄŁ
    -0.65
    soType
    -0.64
    lished
    -0.63
    Ī
    -0.63
    POSITIVE LOGITS
    hip
    1.72
    hips
    1.47
    pace
    1.38
    '
    1.35
    paces
    1.20
    ']
    1.16
    '/
    1.10
    peak
    1.06
    cript
    1.06
    '-
    1.06
    Activations Density 0.459%

    No Known Activations