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. 5590
    Prev
    Next
    INDEX
    Explanations

    calls to action or suggested actions in messages formatted as bullet points or lists

    oai_token-act-pair · gpt-3.5-turbo

    calls to action or instructions for engagement

    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
     TRI
    -0.91
     Blanc
    -0.70
    TERN
    -0.69
     Harbour
    -0.69
     LC
    -0.69
     subst
    -0.67
     CFL
    -0.65
     242
    -0.64
     CET
    -0.61
     243
    -0.61
    POSITIVE LOGITS
    you
    1.16
     you
    1.08
     You
    0.95
     YOU
    0.93
    You
    0.90
    fml
    0.84
    YOU
    0.77
    ayne
    0.77
     your
    0.73
    =~
    0.70
    Activations Density 0.179%

    No Known Activations