© 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. 30365
    Prev
    Next
    INDEX
    Explanations

    legal terms and conditions related to regulations

    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
    626
    +0.13
    0.6%
    125
    +0.12
    0.5%
    623
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    365
    +0.13
    0.01
    455
    +0.12
    0.09
    408
    +0.09
    0.11
    Negative Logits
    DragonMagazine
    -0.78
    united
    -0.75
    EStream
    -0.71
    ython
    -0.68
    Tes
    -0.67
     Nath
    -0.67
    uden
    -0.66
     Awakens
    -0.65
    Insp
    -0.64
    ysc
    -0.64
    POSITIVE LOGITS
     exceptions
    1.59
     exemptions
    1.49
     requirements
    1.41
     penalties
    1.34
     limitations
    1.32
     thresholds
    1.32
     restrictions
    1.32
     deadlines
    1.31
     exemption
    1.30
     criteria
    1.29
    Activations Density 2.008%

    No Known Activations