© 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. 7109
    Prev
    Next
    INDEX
    Explanations

    references to the word "who" in various contexts

    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
    193
    +0.10
    0.4%
    516
    +0.10
    0.4%
    203
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.10
    0.04
    551
    +0.10
    0.04
    762
    +0.09
    0.04
    Negative Logits
    tails
    -0.73
    MENT
    -0.73
    details
    -0.71
     Heck
    -0.71
    NUM
    -0.70
    ARA
    -0.69
    nell
    -0.68
    CLUS
    -0.67
    ANCE
    -0.66
    VA
    -0.66
    POSITIVE LOGITS
     dwell
    0.81
    orned
    0.76
     conqu
    0.75
     consec
    0.73
     uphold
    0.72
     subdu
    0.71
     Thou
    0.70
     hath
    0.69
     comprehend
    0.69
     incarn
    0.68
    Activations Density 0.195%

    No Known Activations