© 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. 28242
    Prev
    Next
    INDEX
    Explanations

    the conjunction "and" 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
    +0.18
    0.8%
    393
    +0.10
    0.5%
    473
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.18
    0.10
    732
    +0.10
    0.03
    728
    +0.10
    0.03
    Negative Logits
    requires
    -0.76
     expires
    -0.73
    ](
    -0.72
    '.
    -0.68
    ................
    -0.68
    .[
    -0.67
    ].
    -0.66
    !".
    -0.65
     considers
    -0.65
    +.
    -0.65
    POSITIVE LOGITS
     its
    0.92
     subsequent
    0.90
     ensuing
    0.89
     others
    0.88
     consequ
    0.87
     accompanying
    0.85
    rogens
    0.84
     other
    0.83
     resultant
    0.80
     attendant
    0.79
    Activations Density 1.038%

    No Known Activations