© 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. 8-RES_POST_32K-OAI
    11. 7510
    Prev
    Next
    INDEX
    Explanations

    mentions of awards and accolades in the context of notable individuals

    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
    373
    +0.14
    0.6%
    493
    +0.10
    0.5%
    561
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.14
    0.07
    627
    +0.10
    -0.01
    610
    +0.10
    0.03
    Negative Logits
     Documentation
    -0.89
    ctory
    -0.85
     administr
    -0.84
    Tact
    -0.82
    RFC
    -0.79
     mathemat
    -0.78
    Summary
    -0.77
     [&
    -0.77
     Strongh
    -0.77
    abwe
    -0.77
    POSITIVE LOGITS
     celeb
    1.39
     Beyon
    1.26
     Instagram
    1.25
     Grammy
    1.25
     Kardashian
    1.23
     TMZ
    1.21
     Gaga
    1.20
     Playboy
    1.20
     celebrities
    1.19
     onstage
    1.18
    Activations Density 12.061%

    No Known Activations