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. 11-RES-JB
    6. 8072
    Prev
    Next
    INDEX
    Explanations

    instances where there is an indication of something that has not happened or been completed yet

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "yet" indicating something is incomplete or not finalized

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gang
    -0.80
    ufact
    -0.76
    ãĥ³ãĤ¸
    -0.63
    rador
    -0.63
    chio
    -0.63
     streng
    -0.63
    natureconservancy
    -0.62
    asus
    -0.59
     disproportion
    -0.59
    ¥µ
    -0.57
    POSITIVE LOGITS
    hin
    0.76
    abouts
    0.76
     anyway
    0.75
    terday
    0.73
     anyways
    0.72
    èª
    0.72
    .
    0.70
     :(
    0.69
    !
    0.68
    !!
    0.65
    Activations Density 0.030%

    No Known Activations