© 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. 28141
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or matrix structures

    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
    316
    +0.14
    0.6%
    688
    +0.12
    0.5%
    422
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.14
    0.04
    326
    +0.12
    0.06
    314
    +0.10
    -0.01
    Negative Logits
    ournal
    -0.81
    ername
    -0.81
    lihood
    -0.81
    FTWARE
    -0.79
    ebook
    -0.77
    abases
    -0.75
    Frameworks
    -0.75
    istries
    -0.74
    aukee
    -0.72
    DonaldTrump
    -0.71
    POSITIVE LOGITS
    rm
    0.76
     02
    0.74
     cyl
    0.74
     fr
    0.73
     visc
    0.72
     03
    0.70
    pic
    0.70
     01
    0.69
    vm
    0.64
     dusk
    0.64
    Activations Density 0.403%

    No Known Activations