© 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. 27655
    Prev
    Next
    INDEX
    Explanations

    terms related to licensing and content distribution

    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
    373
    +0.19
    0.9%
    211
    +0.10
    0.5%
    319
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.19
    -0.01
    211
    +0.10
    0.01
    39
    +0.10
    0.01
    Negative Logits
    RAW
    -0.67
    Ô
    -0.66
     proble
    -0.66
    lain
    -0.66
    omew
    -0.65
    ivas
    -0.65
    ntil
    -0.63
    iban
    -0.63
    nox
    -0.63
    ython
    -0.63
    POSITIVE LOGITS
     obtaining
    0.62
     lawfully
    0.58
     Gutenberg
    0.57
    Angel
    0.56
    Lic
    0.56
     receiving
    0.55
     patented
    0.54
     licens
    0.53
    911
    0.53
     without
    0.52
    Activations Density 0.093%

    No Known Activations