© 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. 12904
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative impacts or consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "toll" as it applies to costs, consequences, or burdens

    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
    RGB
    -0.84
     Correspond
    -0.71
     Prix
    -0.65
    PRESS
    -0.63
     Appearance
    -0.63
    SOURCE
    -0.63
    raised
    -0.62
    Knight
    -0.62
     Sketch
    -0.62
    pat
    -0.62
    POSITIVE LOGITS
     toll
    1.31
     booths
    0.97
     Toll
    0.84
     Dickinson
    0.83
     plaza
    0.79
     traged
    0.79
     booth
    0.77
     cooker
    0.77
     crane
    0.76
    sylvania
    0.76
    Activations Density 0.005%

    No Known Activations