© 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. 8-RES_POST_32K-OAI
    11. 5076
    Prev
    Next
    INDEX
    Explanations

    references to a specific course or educational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    575
    +0.10
    0.5%
    17
    +0.09
    0.4%
    113
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.10
    0.02
    575
    +0.09
    0.02
    225
    +0.09
    0.02
    Negative Logits
    alty
    -0.67
    thening
    -0.65
    axter
    -0.61
    mented
    -0.61
    hap
    -0.60
    Mini
    -0.59
     rites
    -0.58
    nesday
    -0.58
     IMAGES
    -0.57
     Kingdoms
    -0.57
    POSITIVE LOGITS
    course
    0.90
    books
    0.83
    meal
    0.82
    fare
    0.81
    Course
    0.78
    washer
    0.76
    ibur
    0.75
    keeper
    0.72
    book
    0.71
    work
    0.70
    Activations Density 0.078%

    No Known Activations