© 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. 31303
    Prev
    Next
    INDEX
    Explanations

    instances of speech and communication 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
    184
    +0.11
    0.5%
    436
    +0.10
    0.5%
    459
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.11
    -0.01
    755
    +0.10
    0.01
    631
    +0.10
    0.01
    Negative Logits
     tiss
    -0.68
    vier
    -0.64
     Goldberg
    -0.63
     Chains
    -0.62
     bondage
    -0.61
     tag
    -0.61
    etz
    -0.59
     Unch
    -0.58
    zed
    -0.58
    gery
    -0.58
    POSITIVE LOGITS
    é¾įå¥ij士
    0.75
    åħī
    0.69
    ãĥĨãĤ£
    0.68
    acity
    0.67
    ython
    0.65
    ilo
    0.64
    aire
    0.64
    avier
    0.63
    ore
    0.60
    thinkable
    0.60
    Activations Density 0.045%

    No Known Activations