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. 6-RES-JB
    6. 8820
    Prev
    Next
    INDEX
    Explanations

    locations or events related to the town of Corsica

    oai_token-act-pair · gpt-3.5-turbo

    references to locations and events related to "Corsica" and "sodomy."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inez
    -0.73
    ITED
    -0.71
    ded
    -0.68
    ding
    -0.66
    theless
    -0.66
    vous
    -0.60
    packing
    -0.59
    urrent
    -0.57
     doubted
    -0.56
    yrinth
    -0.56
    POSITIVE LOGITS
    herer
    1.05
    oms
    0.97
    opher
    0.94
    ãĥ´
    0.94
    obar
    0.86
    heastern
    0.86
    Sov
    0.83
    wick
    0.83
    rils
    0.81
    ivil
    0.80
    Activations Density 0.047%

    No Known Activations