© 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. 10-RES_POST_32K-OAI
    11. 29192
    Prev
    Next
    INDEX
    Explanations

    references to academic or scholarly work

    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
    11
    +0.12
    0.6%
    599
    +0.11
    0.5%
    397
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    540
    +0.12
    0.15
    641
    +0.11
    0.13
    679
    +0.11
    0.18
    Negative Logits
     Cancel
    -0.88
     Disable
    -0.81
    ptoms
    -0.76
     Freeze
    -0.72
     shitty
    -0.70
     poop
    -0.69
    Exit
    -0.69
     punishments
    -0.69
     thrott
    -0.69
     punish
    -0.69
    POSITIVE LOGITS
     scholarly
    1.42
     scholarship
    1.30
     invaluable
    1.19
     histor
    1.17
     scholars
    1.15
     essays
    1.13
     eluc
    1.13
     fruitful
    1.12
     methodological
    1.08
     illuminating
    1.06
    Activations Density 5.505%

    No Known Activations