© 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. 6278
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Mc" or its variants in the text

    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
    16
    +0.10
    0.5%
    141
    +0.10
    0.5%
    533
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.10
    0.04
    508
    +0.10
    0.02
    382
    +0.10
    0.02
    Negative Logits
    itect
    -0.71
    umed
    -0.66
    orative
    -0.65
    owicz
    -0.60
     Alchemist
    -0.60
    ulhu
    -0.59
    ographed
    -0.59
    ressed
    -0.58
     sund
    -0.57
     receptive
    -0.57
    POSITIVE LOGITS
    Afee
    1.11
    lean
    1.00
    Donnell
    0.91
    gee
    0.89
    Govern
    0.89
    Ale
    0.82
    Fla
    0.80
     Klux
    0.80
    Daniel
    0.79
    donald
    0.79
    Activations Density 0.025%

    No Known Activations