© 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. 27338
    Prev
    Next
    INDEX
    Explanations

    terms related to elevation or enhancement

    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
    274
    +0.12
    0.5%
    204
    +0.10
    0.5%
    311
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.03
    288
    +0.10
    0.03
    526
    +0.10
    0.00
    Negative Logits
    ãģ¦
    -0.86
     system
    -0.72
    edom
    -0.64
     Comet
    -0.62
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.61
     CBI
    -0.60
    plex
    -0.60
     Britann
    -0.60
     contrad
    -0.59
     unfocusedRange
    -0.59
    POSITIVE LOGITS
    ifted
    1.29
    ended
    1.28
    enders
    1.28
    ocking
    1.27
    ift
    1.27
    ension
    1.26
    ocks
    1.24
    inking
    1.23
    ink
    1.22
    ifting
    1.22
    Activations Density 0.103%

    No Known Activations