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. 9-RES-JB
    6. 8166
    Prev
    Next
    INDEX
    Explanations

    government-related terms and agencies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     verses
    -0.77
     jars
    -0.75
     goats
    -0.72
     somew
    -0.71
     candles
    -0.70
     kisses
    -0.70
    ibling
    -0.70
     dogs
    -0.69
    ashtra
    -0.68
     fractured
    -0.67
    POSITIVE LOGITS
     Personnel
    1.14
     Strategic
    1.08
     Management
    1.04
     Inquiry
    1.03
     Communications
    1.02
     Compliance
    1.02
     Information
    0.97
     Naval
    0.92
     Inspector
    0.91
     Advisory
    0.91
    Activations Density 0.046%

    No Known Activations