© 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. 31993
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the concept of "the" in various contexts

    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
    362
    +0.32
    1.7%
    393
    +0.25
    1.4%
    608
    +0.21
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.32
    0.57
    608
    +0.25
    0.43
    393
    +0.21
    0.35
    Negative Logits
     namely
    -0.91
    thood
    -0.91
     without
    -0.88
     besides
    -0.88
     whilst
    -0.86
    adays
    -0.86
     because
    -0.86
     according
    -0.86
     with
    -0.86
    !
    -0.83
    POSITIVE LOGITS
     slightest
    1.47
     entirety
    1.41
     latter
    1.38
     aforementioned
    1.36
     remainder
    1.29
     entire
    1.29
     same
    1.24
     simplest
    1.17
     smallest
    1.17
    oret
    1.13
    Activations Density 5.547%

    No Known Activations