© 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. 10-RES-JB
    11. 7879
    Prev
    Next
    INDEX
    Explanations

    names of universities and organizations with geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    specific organizations, institutions, or entities, particularly in an academic or governmental context

    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
     blues
    -0.84
     bleed
    -0.78
     trickle
    -0.75
     chatter
    -0.73
     selfies
    -0.73
    lins
    -0.71
     quieter
    -0.71
     blaster
    -0.70
     steal
    -0.70
     backlash
    -0.70
    POSITIVE LOGITS
     Directorate
    1.00
     Division
    0.96
     hereby
    0.96
     Subcommittee
    0.94
     Headquarters
    0.93
     respectively
    0.93
     Publication
    0.92
    .''.
    0.92
     Faculty
    0.90
     pursuant
    0.90
    Activations Density 0.414%

    No Known Activations