© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4520
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" and related storytelling elements

    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
    374
    +0.12
    0.5%
    321
    +0.10
    0.4%
    718
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.12
    0.07
    608
    +0.10
    0.06
    393
    +0.10
    0.05
    Negative Logits
    ãĥ¡
    -0.77
     illumination
    -0.68
    lihood
    -0.68
    FIELD
    -0.64
    ãĤ¼ãĤ¦ãĤ¹
    -0.63
    anguages
    -0.62
    _-
    -0.61
     ISBN
    -0.61
    icut
    -0.61
    motion
    -0.59
    POSITIVE LOGITS
     assembled
    0.96
     interviewer
    0.91
     astonished
    0.86
     gathered
    0.81
     contrary
    0.77
     congregation
    0.75
     reporters
    0.72
     tale
    0.72
     crowd
    0.72
     horrified
    0.71
    Activations Density 0.362%

    No Known Activations