© 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 EvalsExportsinterp-engineNEWAPI 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. 26976
    Prev
    Next
    INDEX
    Explanations

    numerical representations or variables in mathematical expressions

    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
    684
    +0.13
    0.6%
    373
    +0.09
    0.4%
    244
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    159
    +0.13
    0.01
    511
    +0.09
    0.01
    752
    +0.09
    0.02
    Negative Logits
    cised
    -0.65
    esy
    -0.65
    olit
    -0.64
    ioned
    -0.62
    ppings
    -0.62
    skirts
    -0.62
    bench
    -0.61
    ortment
    -0.61
     pockets
    -0.60
    past
    -0.60
    POSITIVE LOGITS
    =[
    0.80
    actionDate
    0.65
     axis
    0.65
    =]
    0.65
     turns
    0.63
    soType
    0.60
    ]-
    0.60
    VEL
    0.59
     specify
    0.59
    ainted
    0.59
    Activations Density 0.090%

    No Known Activations