© 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. 8-RES_POST_32K-OAI
    11. 6325
    Prev
    Next
    INDEX
    Explanations

    questions that begin with "Why."

    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
    +0.17
    0.8%
    331
    +0.11
    0.5%
    572
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    300
    +0.17
    0.04
    628
    +0.11
    0.04
    572
    +0.10
    0.04
    Negative Logits
    interstitial
    -0.67
     nearer
    -0.57
     possession
    -0.55
     polymorph
    -0.55
     distribut
    -0.54
     Vert
    -0.53
     reefs
    -0.52
    natureconservancy
    -0.52
     determining
    -0.51
     respectively
    -0.51
    POSITIVE LOGITS
    ?!
    0.74
    oeuv
    0.74
     kidding
    0.71
    Dat
    0.71
    Wait
    0.70
    ????????
    0.69
    ?!"
    0.69
     else
    0.69
    nam
    0.64
    ????
    0.64
    Activations Density 0.066%

    No Known Activations