© 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. 30426
    Prev
    Next
    INDEX
    Explanations

    quotes or dialogue within the text

    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
    102
    +0.16
    0.7%
    720
    +0.13
    0.6%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.16
    0.12
    160
    +0.13
    0.12
    107
    +0.10
    0.09
    Negative Logits
     Referred
    -0.78
     redes
    -0.73
    iership
    -0.68
     Reserved
    -0.68
     reel
    -0.67
     appre
    -0.66
     accomp
    -0.64
     extraord
    -0.63
     rematch
    -0.62
     partName
    -0.62
    POSITIVE LOGITS
    there
    1.87
    they
    1.59
    it
    1.54
    we
    1.54
    everyone
    1.50
    these
    1.49
    you
    1.42
    everything
    1.39
    the
    1.38
    when
    1.37
    Activations Density 0.520%

    No Known Activations