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

    Neuronpedia

    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. 29585
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "McCarthy" in various contexts

    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
    659
    +0.16
    0.7%
    19
    +0.14
    0.7%
    314
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.16
    0.04
    19
    +0.14
    0.02
    538
    +0.12
    0.02
    Negative Logits
     unprotected
    -0.75
     ACS
    -0.70
     untreated
    -0.66
     Acts
    -0.63
     misunderstood
    -0.63
     AE
    -0.63
     incumbent
    -0.63
     Aval
    -0.62
    200000
    -0.61
     awaiting
    -0.61
    POSITIVE LOGITS
    Afee
    1.45
    Kin
    1.43
    Leod
    1.37
    Connell
    1.36
    Lean
    1.35
    Queen
    1.24
    Far
    1.23
    Bride
    1.23
    Neil
    1.22
    Donnell
    1.21
    Activations Density 0.036%

    No Known Activations