© 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. 27303
    Prev
    Next
    INDEX
    Explanations

    superlative adjectives that indicate quality or significance

    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
    713
    +0.11
    0.5%
    307
    +0.09
    0.4%
    459
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.11
    0.05
    400
    +0.09
    0.03
    623
    +0.09
    0.03
    Negative Logits
    hyde
    -0.87
    ãĤ´ãĥ³
    -0.84
    obook
    -0.83
    ologue
    -0.79
     colleague
    -0.77
    è£ħ
    -0.76
     spouse
    -0.76
    timer
    -0.76
    brance
    -0.74
    eanor
    -0.73
    POSITIVE LOGITS
     ways
    1.07
     examples
    1.04
     inventions
    1.00
     avenues
    0.99
     pieces
    0.93
     aspects
    0.93
     pillars
    0.93
     instances
    0.92
     mysteries
    0.92
     representations
    0.92
    Activations Density 0.252%

    No Known Activations