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

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 2031
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise or shock

    oai_token-act-pair · gpt-3.5-turbo

    repeated expressions of surprise or exclamation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 0 - surprise

    No Comments

    Negative Logits
     rib
    -0.70
     prom
    -0.67
     Shore
    -0.66
     consequences
    -0.64
     GR
    -0.64
     corporate
    -0.63
     porch
    -0.63
     Rockies
    -0.63
     Cross
    -0.62
     weed
    -0.62
    POSITIVE LOGITS
    Ah
    3.72
     Ah
    2.26
    Eh
    2.00
    Oh
    1.67
    AH
    1.64
     ah
    1.53
    Ha
    1.47
    Hmm
    1.46
    Um
    1.46
    Uh
    1.44
    Activations Density 0.017%

    No Known Activations