© 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. 30090
    Prev
    Next
    INDEX
    Explanations

    details related to certification and training requirements in technical fields

    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
    415
    +0.12
    0.6%
    524
    +0.10
    0.5%
    62
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    524
    +0.12
    0.10
    415
    +0.10
    0.08
    680
    +0.10
    0.04
    Negative Logits
     gossip
    -0.77
    weet
    -0.75
     unaccount
    -0.74
     leaks
    -0.73
     suspic
    -0.72
     greedy
    -0.71
     TMZ
    -0.71
     Samson
    -0.69
     landsl
    -0.69
    Reply
    -0.68
    POSITIVE LOGITS
     courses
    1.71
    Course
    1.62
     curriculum
    1.56
     Course
    1.43
     Instructor
    1.42
    ourses
    1.39
     semester
    1.38
     curric
    1.38
     course
    1.38
     instructor
    1.36
    Activations Density 2.834%

    No Known Activations