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. 2-RES-JB
    6. 23013
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "boo" and its variations, indicating expressions of disapproval or rejection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to expressing disapproval or scorn, such as 'boo' and 'squee'

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idency
    -0.79
    nesota
    -0.75
    ULTS
    -0.74
    omaly
    -0.74
    pmwiki
    -0.72
    aunder
    -0.72
    tein
    -0.69
    odore
    -0.68
    olars
    -0.67
    negie
    -0.67
    POSITIVE LOGITS
     boo
    1.38
    gey
    1.19
    gee
    0.94
    hovah
    0.92
    Boo
    0.89
     Boo
    0.87
    eful
    0.86
    hello
    0.84
     Tiff
    0.79
     dur
    0.75
    Activations Density 0.005%

    No Known Activations