© 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. 28411
    Prev
    Next
    INDEX
    Explanations

    references to the sequence of points or sections in a text

    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
    194
    +0.12
    0.5%
    373
    +0.10
    0.5%
    378
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    402
    +0.12
    0.06
    530
    +0.10
    0.05
    616
    +0.10
    0.06
    Negative Logits
     978
    -0.71
    umers
    -0.64
    ourning
    -0.63
    BuyableInstoreAndOnline
    -0.63
     mates
    -0.59
    issance
    -0.58
    acent
    -0.57
    itness
    -0.57
    ¬¼
    -0.56
    bers
    -0.55
    POSITIVE LOGITS
     section
    1.13
     subparagraph
    1.13
     paragraph
    1.11
     part
    1.01
     sentence
    0.99
     clause
    0.97
     criterion
    0.93
     subsection
    0.92
     excerpt
    0.92
     paragraphs
    0.91
    Activations Density 0.453%

    No Known Activations