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. 9-RES-JB
    6. 377
    Prev
    Next
    INDEX
    Explanations

    references to specific dates or periods of time

    oai_token-act-pair · gpt-3.5-turbo

    historical references and significant time-related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ONSORED
    -0.66
    Vice
    -0.61
    ãĥ¼ãĥ³
    -0.56
    ãĥĦ
    -0.54
    enegger
    -0.54
    Nonetheless
    -0.53
     itself
    -0.52
    Runner
    -0.51
    \\\\\\\\
    -0.50
    Attempt
    -0.50
    POSITIVE LOGITS
     converge
    0.74
     collide
    0.73
     vary
    0.70
     differ
    0.69
     abound
    0.64
     varying
    0.63
     aren
    0.62
     backgrounds
    0.61
     are
    0.60
     prolifer
    0.60
    Activations Density 1.249%

    No Known Activations