© 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. 28027
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their associated emotional expressions

    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
    314
    +0.27
    1.3%
    373
    +0.13
    0.6%
    666
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.27
    0.17
    253
    +0.13
    0.17
    489
    +0.10
    0.16
    Negative Logits
     Mechdragon
    -0.66
     favour
    -0.65
     contrad
    -0.63
     favourable
    -0.63
     cod
    -0.62
     nodd
    -0.61
     sclerosis
    -0.61
     aur
    -0.60
     mould
    -0.60
     prevailed
    -0.60
    POSITIVE LOGITS
    _.
    1.36
     .
    1.33
    Pa
    1.12
    -.
    1.05
    @
    0.98
     ."
    0.97
    pdf
    0.96
    gif
    0.95
    ,.
    0.90
    gov
    0.89
    Activations Density 2.326%

    No Known Activations