© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 7847
    Prev
    Next
    INDEX
    Explanations

    personal reflections or introspection

    oai_token-act-pair · gpt-3.5-turbo

    statements expressing personal identity or self-awareness

    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
    angering
    -0.70
    Detailed
    -0.69
    SpaceEngineers
    -0.67
     targeting
    -0.67
    Officials
    -0.66
    Leaks
    -0.65
    Consumer
    -0.65
    CPU
    -0.63
    Intel
    -0.63
    Demand
    -0.63
    POSITIVE LOGITS
     autobi
    1.13
     kindred
    0.92
     poet
    0.91
     Twain
    0.87
     biography
    0.86
     psychologist
    0.86
     poems
    0.85
     novelist
    0.85
     autobiography
    0.84
     narrator
    0.82
    Activations Density 1.482%

    No Known Activations