© 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. 8-RES-JB
    11. 188
    Prev
    Next
    INDEX
    Explanations

    references to specific names, titles, or projects

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to media content, personalities, and institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hague
    -0.73
    efully
    -0.69
    imil
    -0.68
     LAST
    -0.66
     Gors
    -0.66
    ãĤ¨
    -0.63
    èĢ
    -0.63
     <[
    -0.60
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.60
    é¾įåĸļ士
    -0.59
    POSITIVE LOGITS
     sightings
    0.89
     sighting
    0.85
     employee
    0.82
    âĦ¢
    0.81
     devote
    0.80
     alumni
    0.79
     themed
    0.78
     product
    0.78
     employees
    0.76
     clones
    0.76
    Activations Density 0.620%

    No Known Activations