© 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. 0-RES-JB
    11. 8279
    Prev
    Next
    INDEX
    Explanations

    exclamations suggesting surprise or disbelief

    oai_token-act-pair · gpt-3.5-turbo

    expressions of surprise or strong emotion

    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
     certain
    -0.70
     generally
    -0.64
     partly
    -0.63
     general
    -0.61
     broadly
    -0.61
     similar
    -0.60
     grav
    -0.60
     various
    -0.60
     predominantly
    -0.58
     principally
    -0.58
    POSITIVE LOGITS
    ?!
    2.56
    !!
    2.45
    !!!
    2.38
    !!!!
    2.27
    !!!!!
    2.22
    !",
    2.16
    !".
    2.13
    !
    2.12
    !),
    2.08
    !).
    2.05
    Activations Density 0.032%

    No Known Activations