Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 6971
    Prev
    Next
    INDEX
    Explanations

    exclamatory interjections or expressions of surprise

    oai_token-act-pair · gpt-3.5-turbo

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Pub
    -0.70
    Prior
    -0.68
    Prem
    -0.66
    emi
    -0.64
    ESE
    -0.64
    ences
    -0.61
    Abstract
    -0.61
    és
    -0.59
    Dem
    -0.59
     Associates
    -0.58
    POSITIVE LOGITS
     oh
    3.54
     Oh
    1.62
    Oh
    1.49
    ohm
    1.41
     wow
    1.39
     ah
    1.38
    oh
    1.37
     hey
    1.36
     uh
    1.33
     eh
    1.32
    Activations Density 0.012%

    No Known Activations