© 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. 10-RES-JB
    11. 2838
    Prev
    Next
    INDEX
    Explanations

    exclamatory phrases expressing a call to action

    oai_token-act-pair · gpt-3.5-turbo
    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
    undai
    -0.89
    ylum
    -0.72
     disson
    -0.72
     destro
    -0.72
    itated
    -0.71
    yrus
    -0.70
     plurality
    -0.69
     resisting
    -0.67
     compromises
    -0.67
    itates
    -0.66
    POSITIVE LOGITS
    @#&
    1.49
     :)
    1.27
     :-)
    1.19
     ðŁĻĤ
    1.19
     ;)
    1.16
     ðŁĺ
    1.14
    [/
    1.06
    <|endoftext|>
    1.00
     Enjoy
    1.00
    ?!
    0.99
    Activations Density 0.072%

    No Known Activations