© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8-RES_POST_32K-OAI
    11. 4379
    Prev
    Next
    INDEX
    Explanations

    references to studies, methods, and materials in the context of academic discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    314
    +0.12
    0.5%
    194
    +0.09
    0.4%
    680
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    680
    +0.12
    0.06
    739
    +0.09
    0.05
    716
    +0.09
    0.09
    Negative Logits
    veland
    -0.76
    idency
    -0.63
    universal
    -0.62
    biased
    -0.58
    idence
    -0.56
     Mehran
    -0.54
    ococ
    -0.54
    PU
    -0.52
     Clancy
    -0.52
     Wide
    -0.52
    POSITIVE LOGITS
     above
    2.07
    above
    1.83
     below
    1.75
    below
    1.59
     Above
    1.46
     foregoing
    1.43
     listed
    1.30
     BELOW
    1.28
    Above
    1.26
     mentioned
    1.26
    Activations Density 4.331%

    No Known Activations