© 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. 2-RES-JB
    11. 23923
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific character named "Boss"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Boss."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WAYS
    -0.80
    POL
    -0.75
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.72
    OPE
    -0.72
    JUST
    -0.71
    VERTIS
    -0.68
    Û
    -0.68
    igenous
    -0.67
    LIB
    -0.67
    FACE
    -0.66
    POSITIVE LOGITS
    anova
    1.07
    enhagen
    0.99
     Boss
    0.97
    Boss
    0.90
    zilla
    0.87
    es
    0.83
    buster
    0.83
    ilage
    0.80
    adelphia
    0.80
    arella
    0.78
    Activations Density 0.010%

    No Known Activations