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. 8831
    Prev
    Next
    INDEX
    Explanations

    technical terms or phrases related to specific industries or contexts, such as IT, immigration, cooking, and shipping

    oai_token-act-pair · gpt-3.5-turbo

    significant nouns related to processes, structures, or concepts

    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
    å§«
    -0.96
     channels
    -0.80
     levers
    -0.74
     bins
    -0.73
     chapters
    -0.72
    thumbnails
    -0.72
     departments
    -0.72
     territories
    -0.71
     crates
    -0.71
     scenes
    -0.71
    POSITIVE LOGITS
     akin
    0.95
     consisting
    0.93
     thats
    0.82
    ifier
    0.81
    forcer
    0.81
     similar
    0.80
     somewhere
    0.78
     wherein
    0.78
     costing
    0.76
     reminiscent
    0.76
    Activations Density 0.495%

    No Known Activations