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. 8-RES-JB
    6. 9557
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific name, "Bourquin," possibly in different contexts or variations

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of a specific individual's name, particularly variants of "Bour."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.78
    ORTS
    -0.77
    ulse
    -0.77
    ocated
    -0.68
    ogical
    -0.68
    resses
    -0.66
    inson
    -0.65
    sburg
    -0.65
    ional
    -0.64
    ORE
    -0.63
    POSITIVE LOGITS
    geoning
    1.03
    dain
    1.00
    TeX
    0.81
    neys
    0.77
     Rouge
    0.75
     Bour
    0.73
    bons
    0.73
    asso
    0.69
    nam
    0.68
    odies
    0.68
    Activations Density 0.067%

    No Known Activations