© 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. 8-RES_POST_32K-OAI
    11. 7125
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" as well as phrases indicating significance or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    576
    +0.10
    0.5%
    97
    +0.10
    0.5%
    462
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.10
    0.06
    393
    +0.10
    0.04
    608
    +0.10
    0.05
    Negative Logits
    é¾įåĸļ士
    -0.81
    estones
    -0.74
    jas
    -0.69
    ãĤ¨ãĥ«
    -0.66
    icating
    -0.65
    anches
    -0.63
    icates
    -0.62
     bells
    -0.62
    affles
    -0.61
    bats
    -0.60
    POSITIVE LOGITS
     case
    0.85
     scenario
    0.78
     situation
    0.74
     CASE
    0.71
     fate
    0.69
     conclusion
    0.69
     place
    0.64
     location
    0.64
     happen
    0.64
     type
    0.63
    Activations Density 0.210%

    No Known Activations