© 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. 7-RES-JB
    11. 4049
    Prev
    Next
    INDEX
    Explanations

    words related to physical reactions or emotions like groaning, gasping, cringing, freezing, grinning, and crying

    oai_token-act-pair · gpt-3.5-turbo

    emotional or expressive reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    available
    -0.74
    DragonMagazine
    -0.72
    trump
    -0.70
    ership
    -0.70
    DonaldTrump
    -0.69
    venth
    -0.68
    arov
    -0.67
    illary
    -0.66
    cour
    -0.66
    ItemImage
    -0.65
    POSITIVE LOGITS
     loudly
    1.05
     uncontroll
    1.04
     violently
    1.03
     bitterly
    0.99
     horribly
    0.94
     miser
    0.94
     angrily
    0.92
     aloud
    0.91
     nervously
    0.90
     furiously
    0.89
    Activations Density 0.141%

    No Known Activations