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. 8-RES-JB
    6. 19486
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to job positions and roles

    oai_token-act-pair · gpt-3.5-turbo

    terms related to business and economic metrics

    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
    inventoryQuantity
    -0.77
    Huh
    -0.62
    ãĥĪ
    -0.62
    fuck
    -0.61
    iversary
    -0.61
    ="#
    -0.60
    RAW
    -0.60
    verse
    -0.59
    rawdownloadcloneembedreportprint
    -0.59
    stop
    -0.58
    POSITIVE LOGITS
     abound
    1.28
     meanwhile
    0.95
     also
    0.92
     included
    0.86
    ŃĶ
    0.84
     prolifer
    0.82
     likewise
    0.80
     therefore
    0.79
    also
    0.76
     ensured
    0.75
    Activations Density 0.403%

    No Known Activations