© 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. 30473
    Prev
    Next
    INDEX
    Explanations

    variables and parameters in a structured data or coding context

    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
    91
    +0.10
    0.5%
    281
    +0.10
    0.4%
    388
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.07
    153
    +0.10
    0.04
    281
    +0.10
    0.02
    Negative Logits
     Goldstein
    -0.79
     Elsa
    -0.77
    Elsa
    -0.77
     Hua
    -0.74
     ISIL
    -0.73
     Cohn
    -0.70
    llan
    -0.68
     Alc
    -0.67
    helm
    -0.67
    Wilson
    -0.67
    POSITIVE LOGITS
     4
    1.56
    4
    1.55
     Four
    1.11
    four
    1.01
     four
    1.00
    Four
    0.96
     465
    0.91
     IV
    0.90
     470
    0.90
     475
    0.84
    Activations Density 1.538%

    No Known Activations