© 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. 32457
    Prev
    Next
    INDEX
    Explanations

    repeated uses of the pronoun "it."

    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
    348
    +0.13
    0.6%
    361
    +0.11
    0.5%
    259
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    676
    +0.13
    0.12
    213
    +0.11
    0.10
    689
    +0.11
    0.09
    Negative Logits
     Mellon
    -0.71
     moreover
    -0.67
     delegation
    -0.67
     additionally
    -0.66
     credential
    -0.66
     thereby
    -0.66
     methodological
    -0.66
     contends
    -0.65
     exhibits
    -0.64
     contiguous
    -0.64
    POSITIVE LOGITS
     ain
    1.02
     sucked
    0.93
     raining
    0.91
     gonna
    0.90
    ðŁĺ
    0.89
     suck
    0.89
     happ
    0.88
     Ain
    0.88
     WAS
    0.87
     sucks
    0.86
    Activations Density 0.310%

    No Known Activations