© 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. 8-RES-JB
    11. 6340
    Prev
    Next
    INDEX
    Explanations

    exclamations expressing strong emotions or urgency

    oai_token-act-pair · gpt-3.5-turbo

    exclamatory statements or expressions of strong emotion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -0.74
     tremend
    -0.73
    bda
    -0.71
     scattering
    -0.68
     dispers
    -0.66
     casting
    -0.65
    conservancy
    -0.64
     psychiat
    -0.64
    wagen
    -0.63
     photograp
    -0.63
    POSITIVE LOGITS
    ¬
    1.03
    ľ
    1.00
    º
    0.93
    ¦
    0.92
    ĭ
    0.89
    £
    0.87
    ļ
    0.85
    Ĵ
    0.84
    ª
    0.84
    Ķ
    0.83
    Activations Density 0.234%

    No Known Activations