© 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 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. 7028
    Prev
    Next
    INDEX
    Explanations

    references to the word "supreme" and related concepts

    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
    739
    +0.15
    0.7%
    496
    +0.12
    0.5%
    202
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    19
    +0.15
    0.01
    343
    +0.12
    0.01
    555
    +0.12
    0.01
    Negative Logits
    ttes
    -0.75
    pox
    -0.70
    Lens
    -0.69
     Lauder
    -0.68
    ãĥĥãĤ¯
    -0.66
    OME
    -0.66
     Trave
    -0.64
     Remastered
    -0.64
     Graveyard
    -0.63
    hyde
    -0.63
    POSITIVE LOGITS
    reme
    1.36
    ersed
    1.15
    olicy
    1.11
    rompt
    1.02
    rising
    1.00
    urb
    0.99
    ra
    0.98
    ortun
    0.96
    rab
    0.95
    ral
    0.95
    Activations Density 0.055%

    No Known Activations