© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12652
    Prev
    Next
    INDEX
    Explanations

    expressions of strong emotions and intense reactions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong emotional reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     principally
    -0.67
    ourses
    -0.64
     âĢİ
    -0.62
     opposition
    -0.62
    lihood
    -0.62
     subsistence
    -0.61
    lements
    -0.60
     materially
    -0.60
     primarily
    -0.59
     disparate
    -0.58
    POSITIVE LOGITS
    eeee
    1.11
    oooooooooooooooo
    1.07
    oooooooo
    1.07
    !!!!!
    1.02
     gotta
    1.02
    !!!!
    1.00
    !!!
    0.97
    ?!
    0.95
    OOOO
    0.94
    EEEE
    0.93
    Activations Density 0.872%

    No Known Activations