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. 18243
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal activities or interests

    oai_token-act-pair · gpt-3.5-turbo

    themes related to leisure activities and enjoyment

    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
    ilion
    -0.76
    aye
    -0.66
     HSBC
    -0.66
    icipated
    -0.66
     ratification
    -0.65
    lihood
    -0.64
    ortium
    -0.64
    elled
    -0.64
     Emin
    -0.62
    trak
    -0.61
    POSITIVE LOGITS
     stunts
    0.82
     underdog
    0.81
     metaphors
    0.81
     weddings
    0.76
     desserts
    0.75
     gadgets
    0.73
     sweets
    0.73
     rhythms
    0.72
     outdoors
    0.72
     gimm
    0.71
    Activations Density 0.707%

    No Known Activations