© 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. 26808
    Prev
    Next
    INDEX
    Explanations

    calls to action and associated promotional phrases

    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
    182
    +0.12
    0.6%
    255
    +0.10
    0.5%
    378
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.12
    0.09
    353
    +0.10
    0.01
    393
    +0.10
    0.14
    Negative Logits
     Nare
    -0.77
    ©¶æ¥µ
    -0.75
    gypt
    -0.75
    gyn
    -0.75
    font
    -0.74
     Gord
    -0.74
    Len
    -0.73
    ogyn
    -0.73
    Doug
    -0.72
     Sloven
    -0.72
    POSITIVE LOGITS
    Action
    1.86
     Action
    1.85
     action
    1.81
    action
    1.80
     Actions
    1.80
    actions
    1.73
     actions
    1.70
     ACTION
    1.61
    ACTION
    1.58
    activity
    1.52
    Activations Density 3.826%

    No Known Activations