© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 11951
    Prev
    Next
    INDEX
    Explanations

    mentions of the country Germany

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "German."

    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
    ctica
    -0.82
    okemon
    -0.81
    tis
    -0.80
    ouston
    -0.79
    ramid
    -0.79
    mble
    -0.77
    esty
    -0.74
    BOOK
    -0.74
    heres
    -0.74
    ipt
    -0.74
    POSITIVE LOGITS
    wings
    1.01
     Chancellor
    0.95
     shepherd
    0.91
     Bundesliga
    0.88
     Shepherd
    0.79
    £ı
    0.76
    oslov
    0.74
     Reich
    0.74
     MEP
    0.73
     chancellor
    0.72
    Activations Density 0.017%

    No Known Activations