© 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. 30391
    Prev
    Next
    INDEX
    Explanations

    occurrences of the verb "have" and its variations in 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
    671
    +0.09
    0.4%
    205
    +0.09
    0.4%
    636
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    344
    +0.09
    0.07
    566
    +0.09
    0.06
    7
    +0.09
    0.06
    Negative Logits
    always
    -0.88
    soType
    -0.80
    nos
    -0.71
     always
    -0.71
     ALWAYS
    -0.70
     confidentiality
    -0.69
     Variant
    -0.69
     never
    -0.68
    ItemThumbnailImage
    -0.67
     Cosponsors
    -0.67
    POSITIVE LOGITS
     finished
    1.32
     completed
    1.11
     exhausted
    0.96
     vanquished
    0.91
    pleted
    0.89
     finish
    0.86
     elapsed
    0.85
     finalized
    0.84
     healed
    0.81
     cleared
    0.81
    Activations Density 0.235%

    No Known Activations