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. 10-RES-JB
    6. 17107
    Prev
    Next
    INDEX
    Explanations

    specific prepositions followed by nouns indicative of actions or associations

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the word "on."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oola
    -0.71
    çͰ
    -0.70
    rina
    -0.69
    ihara
    -0.67
    Definition
    -0.67
    inx
    -0.66
    otle
    -0.61
    ocus
    -0.60
    ####
    -0.60
    ¯¯
    -0.59
    POSITIVE LOGITS
     behalf
    1.82
    site
    1.29
     campuses
    1.19
     occasion
    1.13
     Sundays
    1.12
     weekends
    1.12
    erous
    1.12
     Saturdays
    1.11
    shore
    1.07
     campus
    1.06
    Activations Density 0.182%

    No Known Activations