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. 11-RES-JB
    6. 16954
    Prev
    Next
    INDEX
    Explanations

    proper nouns and titles specifically related to the development or creation of various media or products

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the production and development of various artistic works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MORE
    -0.64
    natureconservancy
    -0.62
    VERTISEMENT
    -0.56
     Scouting
    -0.55
    Commerce
    -0.55
    ases
    -0.55
     Stability
    -0.55
    afa
    -0.54
    etus
    -0.54
    SPONSORED
    -0.53
    POSITIVE LOGITS
     by
    1.18
     jointly
    1.12
     collabor
    1.01
     specifically
    0.95
     exclusively
    0.94
     entirely
    0.93
     independently
    0.91
     using
    0.87
     expressly
    0.86
     specially
    0.86
    Activations Density 0.119%

    No Known Activations