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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 11596
    Prev
    Next
    INDEX
    Explanations

    words that start with "Tr" and have a specific ending

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "Tr" followed by a number

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ELS
    -0.78
    WARE
    -0.77
    manship
    -0.71
    ãģ®éŃĶ
    -0.69
     arts
    -0.68
     Mechdragon
    -0.68
    lihood
    -0.66
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.65
     Aman
    -0.63
    âĸ¬âĸ¬
    -0.63
    POSITIVE LOGITS
    ainer
    1.31
    ained
    1.17
    acer
    1.17
    unks
    1.17
    umps
    1.14
    ains
    1.12
    itton
    1.11
    unk
    1.10
    icky
    1.08
    unn
    1.08
    Activations Density 0.023%

    No Known Activations