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. 4-RES-JB
    6. 22812
    Prev
    Next
    INDEX
    Explanations

    the word "ah" in various contexts with different emphases or forms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the expression "ah" or similar vocalizations

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

    No Comments

    Negative Logits
     nomine
    -0.77
     advoc
    -0.74
     gobl
    -0.74
     fict
    -0.71
     seiz
    -0.70
     paycheck
    -0.68
     drawer
    -0.66
     manifold
    -0.66
     symp
    -0.66
    pmwiki
    -0.65
    POSITIVE LOGITS
    renheit
    1.43
    awk
    1.42
    awks
    1.29
    aha
    1.17
    olics
    1.14
    ttp
    1.05
    tml
    1.03
    onda
    1.00
    oe
    0.95
    orses
    0.95
    Activations Density 0.016%

    No Known Activations