© 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. 29713
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'd' 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
    745
    +0.14
    0.7%
    234
    +0.12
    0.6%
    415
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.14
    0.07
    613
    +0.12
    0.05
    659
    +0.11
    0.06
    Negative Logits
    Interstitial
    -0.69
    dq
    -0.69
    iman
    -0.65
    yx
    -0.64
    ersed
    -0.63
     "$:/
    -0.63
    wcs
    -0.63
     scram
    -0.61
    033
    -0.61
    EStreamFrame
    -0.61
    POSITIVE LOGITS
    iety
    0.82
    aughters
    0.78
    amental
    0.70
    ceiver
    0.69
    uked
    0.67
    ospels
    0.66
    ynasty
    0.66
    hood
    0.65
    omination
    0.65
    ictions
    0.65
    Activations Density 0.687%

    No Known Activations