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. 8612
    Prev
    Next
    INDEX
    Explanations

    verbs in present participle form used in the context of placing or arranging objects

    oai_token-act-pair · gpt-3.5-turbo

    the word "laying" in various contexts

    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
    Sport
    -0.67
     Score
    -0.63
    pmwiki
    -0.63
    orts
    -0.61
     [+
    -0.60
    FS
    -0.59
     Smile
    -0.59
    requently
    -0.57
    rose
    -0.57
     Source
    -0.57
    POSITIVE LOGITS
     laying
    3.63
     lay
    1.75
     laid
    1.73
     lays
    1.69
     lying
    1.62
     shedding
    1.39
     burying
    1.37
    Lay
    1.28
     outlining
    1.20
     assembling
    1.17
    Activations Density 0.007%

    No Known Activations