Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 9338
    Prev
    Next
    INDEX
    Explanations

    terms related to historical and current political and social issues in America and the world

    oai_token-act-pair · gpt-3.5-turbo

    references to historical and contemporary social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exceptions
    -0.64
     backups
    -0.62
     warranties
    -0.61
     backup
    -0.60
     penalties
    -0.59
     Instr
    -0.56
    Same
    -0.55
     inactive
    -0.55
     cardio
    -0.55
     corrid
    -0.54
    POSITIVE LOGITS
    .[
    0.93
    .
    0.88
     embodied
    0.85
     whereby
    0.84
    ."[
    0.83
     wherein
    0.81
    .*
    0.79
     unfolding
    0.77
    —
    0.77
    .'
    0.75
    Activations Density 0.511%

    No Known Activations