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. 9-RES-JB
    6. 12921
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by verbs in present participle form

    oai_token-act-pair · gpt-3.5-turbo

    instances where the word "as" is used to indicate a role or function in a sentence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Os
    -0.83
    akings
    -0.72
    rolet
    -0.72
    irez
    -0.71
    lees
    -0.66
    LINE
    -0.66
    ${
    -0.63
    oes
    -0.62
    ukemia
    -0.62
    Benz
    -0.61
    POSITIVE LOGITS
     leverage
    1.16
     pretext
    0.97
     fodder
    0.93
     excuse
    0.93
     template
    0.89
     ammunition
    0.88
     basis
    0.87
     guideline
    0.86
     camouflage
    0.86
     fertilizer
    0.86
    Activations Density 0.094%

    No Known Activations