© 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. 1-RES-JB
    11. 14589
    Prev
    Next
    INDEX
    Explanations

    references to physical keyboards

    oai_token-act-pair · gpt-3.5-turbo

    references to keyboards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Charity
    -0.74
    IVERS
    -0.74
     Gund
    -0.70
    tics
    -0.70
    ESCO
    -0.69
     Angel
    -0.67
     Lomb
    -0.67
     Directorate
    -0.66
     Forbidden
    -0.66
     Ago
    -0.66
    POSITIVE LOGITS
     keyboard
    1.41
     keyboards
    1.24
     Keyboard
    1.01
     shortcuts
    1.01
     layouts
    0.98
     cursor
    0.94
     dock
    0.92
     touchscreen
    0.91
     shortcut
    0.90
     layout
    0.89
    Activations Density 0.007%

    No Known Activations