Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 18348
    Prev
    Next
    INDEX
    Explanations

    references to financial scams or schemes involving a specific term or location

    oai_token-act-pair · gpt-3.5-turbo

    references to Ponzi schemes and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uncture
    -0.56
     Kinnikuman
    -0.55
    ocamp
    -0.54
    grass
    -0.54
     Mechdragon
    -0.54
     Schne
    -0.53
    ttle
    -0.53
     Canaver
    -0.51
    advertisement
    -0.51
    lav
    -0.51
    POSITIVE LOGITS
    i
    1.52
    is
    1.38
    IS
    1.07
    iology
    1.01
    iologist
    0.98
    iya
    0.97
    isal
    0.95
    ISE
    0.91
    iasm
    0.91
    itiz
    0.90
    Activations Density 0.250%

    No Known Activations