© 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. 28797
    Prev
    Next
    INDEX
    Explanations

    references to manufacturing processes and specifications

    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
    465
    +0.12
    0.5%
    100
    +0.11
    0.5%
    641
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.12
    -0.01
    39
    +0.11
    0.10
    455
    +0.09
    0.12
    Negative Logits
     inaction
    -0.80
    cffffcc
    -0.76
     brainstorm
    -0.71
     lur
    -0.68
     Spur
    -0.68
     tir
    -0.68
     exacerbate
    -0.67
    pmwiki
    -0.67
     tentacles
    -0.67
     punt
    -0.67
    POSITIVE LOGITS
     satisfactory
    1.04
     properly
    1.04
     correct
    1.03
     correctly
    1.01
     specifications
    0.96
     compatible
    0.95
     suitable
    0.95
     acceptable
    0.94
     accurately
    0.93
     proper
    0.92
    Activations Density 5.076%

    No Known Activations