© 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 EvalsExportsinterp-engineNEWAPI 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. 27394
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'C' 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
    +0.19
    0.9%
    260
    +0.12
    0.5%
    674
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.19
    0.09
    67
    +0.12
    0.05
    578
    +0.11
    0.03
    Negative Logits
     lur
    -0.68
     Sloven
    -0.64
     bribes
    -0.63
     repl
    -0.60
     dash
    -0.59
     Eston
    -0.56
     Antar
    -0.56
     Jama
    -0.56
     ob
    -0.55
     replay
    -0.55
    POSITIVE LOGITS
    overed
    1.06
    TS
    1.05
    TF
    1.04
    CS
    1.03
    PP
    1.03
    CC
    1.03
    URRENT
    1.02
    EMENT
    1.02
    AST
    1.02
    EP
    1.02
    Activations Density 0.399%

    No Known Activations