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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 15753
    Prev
    Next
    INDEX
    Explanations

    institutions, organizations, and centers related to health, research, and academia

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to health organizations and research institutions

    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
     ruin
    -0.72
     strangers
    -0.70
     humiliating
    -0.70
     ugly
    -0.70
     mute
    -0.69
     silence
    -0.67
     skinny
    -0.65
     kne
    -0.65
     humiliation
    -0.64
     curtains
    -0.64
    POSITIVE LOGITS
     Collabor
    0.97
     Laboratory
    0.96
     Institute
    0.94
     Fellowship
    0.91
     Consortium
    0.91
     headquartered
    0.91
     Research
    0.88
     Program
    0.87
     Directorate
    0.87
     Subcommittee
    0.86
    Activations Density 0.177%

    No Known Activations