© 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. 30592
    Prev
    Next
    INDEX
    Explanations

    references to application submission processes and procedures

    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
    624
    +0.12
    0.6%
    67
    +0.11
    0.5%
    524
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.12
    0.17
    624
    +0.11
    0.06
    175
    +0.11
    0.04
    Negative Logits
    dies
    -0.78
    Ö
    -0.76
     unle
    -0.72
     Unle
    -0.71
    chant
    -0.71
     revol
    -0.71
     Falling
    -0.68
     outlawed
    -0.66
    roads
    -0.66
     Galile
    -0.66
    POSITIVE LOGITS
     submission
    1.28
     submissions
    1.28
     transcripts
    1.27
     questionnaire
    1.23
     submitting
    1.20
     Submission
    1.20
    Submit
    1.16
     submitted
    1.16
     manuscript
    1.15
     Applicant
    1.11
    Activations Density 6.136%

    No Known Activations