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. 16812
    Prev
    Next
    INDEX
    Explanations

    mentions of the state of Alabama, particularly in relation to people, places, and events occurring within Alabama

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Alabama and its related entities or events

    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
     skate
    -0.97
     Swiss
    -0.97
    ÃŃn
    -0.95
    ijk
    -0.94
     Danish
    -0.94
    pread
    -0.92
     cheese
    -0.92
    án
    -0.91
    Palestinian
    -0.91
    Äĩ
    -0.89
    POSITIVE LOGITS
     Alabama
    2.31
    Alabama
    2.18
     Ala
    1.94
     Auburn
    1.89
     Hunts
    1.86
     Crimson
    1.76
     Birmingham
    1.72
     Saban
    1.69
     Tide
    1.67
     UA
    1.58
    Activations Density 0.197%

    No Known Activations