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. 3-RES-JB
    6. 864
    Prev
    Next
    INDEX
    Explanations

    references to Bavarian locations and aristocratic titles

    oai_token-act-pair · gpt-3.5-turbo

    references to Bavarian culture and geography

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LEASE
    -0.81
    efeated
    -0.75
    figure
    -0.73
    cloth
    -0.69
     partName
    -0.68
    BOOK
    -0.67
    plays
    -0.67
    playing
    -0.67
    _____
    -0.67
     thumbnail
    -0.65
    POSITIVE LOGITS
     Bav
    1.15
    arians
    1.15
    arian
    1.11
    aria
    1.03
    ICAN
    1.00
    olini
    0.88
    illi
    0.84
    ÃĽ
    0.83
     Bam
    0.82
    ç
    0.82
    Activations Density 0.010%

    No Known Activations