© 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. 7568
    Prev
    Next
    INDEX
    Explanations

    references to certain prominent individuals and their ideas or actions

    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
    436
    +0.09
    0.4%
    386
    +0.09
    0.4%
    374
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.09
    0.03
    140
    +0.09
    0.03
    643
    +0.09
    0.02
    Negative Logits
    terday
    -0.84
    akeru
    -0.71
    ãģ®éŃĶ
    -0.69
    erate
    -0.69
     versa
    -0.68
    é»Ĵ
    -0.66
    etheless
    -0.65
    oft
    -0.65
    xual
    -0.62
    ingen
    -0.61
    POSITIVE LOGITS
    achi
    0.88
    rek
    0.84
    ots
    0.83
    anic
    0.82
    ricks
    0.79
    riks
    0.79
    uli
    0.78
    lins
    0.78
    riz
    0.77
    ulus
    0.76
    Activations Density 0.214%

    No Known Activations