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. 5222
    Prev
    Next
    INDEX
    Explanations

    mentions related to entrepreneurship and business activities

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to entrepreneurial ventures and partnerships

    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
     GEAR
    -0.64
     thence
    -0.62
     custody
    -0.61
     thumbs
    -0.61
     indecent
    -0.61
     Sexual
    -0.60
     Kush
    -0.59
     Apps
    -0.58
     sickness
    -0.57
     incident
    -0.57
    POSITIVE LOGITS
    hip
    1.65
    hips
    1.53
    ation
    1.32
    iated
    1.31
    als
    1.30
    edly
    1.23
    ner
    1.21
    ships
    1.20
    ions
    1.20
    er
    1.19
    Activations Density 0.549%

    No Known Activations