© 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. 27922
    Prev
    Next
    INDEX
    Explanations

    references to rockets and rocket-related topics

    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
    286
    +0.13
    0.6%
    269
    +0.12
    0.6%
    268
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.02
    286
    +0.12
    0.01
    269
    +0.12
    0.01
    Negative Logits
    redo
    -0.78
     Borders
    -0.75
    ktop
    -0.74
     Rite
    -0.69
    DonaldTrump
    -0.65
    lihood
    -0.65
     Cullen
    -0.64
     Aad
    -0.63
    oral
    -0.63
     Fargo
    -0.61
    POSITIVE LOGITS
    eers
    1.06
     launcher
    1.05
     propelled
    1.05
     launchers
    1.03
    laun
    0.98
    ry
    0.98
    ulic
    0.89
    Laun
    0.89
     Launcher
    0.88
    eer
    0.87
    Activations Density 0.084%

    No Known Activations