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. 9832
    Prev
    Next
    INDEX
    Explanations

    references to significant or well-known locations such as Notre Dame Cathedral and mentions of the extremist group Boko Haram

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific institutions or groups, particularly "Notre Dame" and "Boko Haram."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     stroke
    -0.73
    prototype
    -0.73
    */(
    -0.72
    ULE
    -0.70
    ulators
    -0.68
    stroke
    -0.68
    storage
    -0.68
    è¦ļéĨĴ
    -0.67
    Rocket
    -0.67
    oted
    -0.65
    POSITIVE LOGITS
     Dame
    1.46
     Notre
    0.96
    heastern
    0.91
     mosqu
    0.80
     adolesc
    0.80
    essor
    0.69
    cipl
    0.69
     Lights
    0.69
    ignt
    0.67
     opio
    0.67
    Activations Density 0.011%

    No Known Activations