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. 15562
    Prev
    Next
    INDEX
    Explanations

    phrases indicating abundance or availability

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "plenty" and its emphasis in various contexts

    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
    issance
    -0.60
    ensis
    -0.57
    istani
    -0.56
    heed
    -0.53
    abad
    -0.53
    ordan
    -0.52
    ibe
    -0.52
    NOR
    -0.51
    ienne
    -0.51
    Aid
    -0.50
    POSITIVE LOGITS
     of
    1.23
     thereof
    1.06
     OF
    0.86
    luster
    0.85
     else
    0.79
    Of
    0.78
     Of
    0.78
    ensical
    0.67
    entimes
    0.67
     plenty
    0.66
    Activations Density 0.065%

    No Known Activations