© 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 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. 29026
    Prev
    Next
    INDEX
    Explanations

    references to variables and their characteristics in programming 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
    623
    +0.13
    0.6%
    540
    +0.12
    0.6%
    109
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.13
    0.03
    540
    +0.12
    0.03
    623
    +0.11
    0.02
    Negative Logits
    llah
    -0.93
    atana
    -0.83
    ļé
    -0.80
    lyak
    -0.79
    lez
    -0.76
    Reply
    -0.76
    hovah
    -0.75
    opot
    -0.74
    Fal
    -0.73
    Ķ
    -0.73
    POSITIVE LOGITS
    ially
    0.77
    ials
    0.75
     names
    0.74
    izable
    0.70
    staking
    0.70
    ention
    0.69
    izations
    0.68
    variable
    0.68
     bindings
    0.68
     assignments
    0.68
    Activations Density 0.089%

    No Known Activations