Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 21012
    Prev
    Next
    INDEX
    Explanations

    phrases related to the U.S. House of Representatives

    oai_token-act-pair · gpt-3.5-turbo

    references to the House of Representatives

    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
    ãĤ¨ãĥ«
    -1.12
    illas
    -0.85
    zsche
    -0.79
    illa
    -0.77
    istically
    -0.77
    istic
    -0.69
    clad
    -0.69
    istical
    -0.68
    ocent
    -0.68
    jad
    -0.67
    POSITIVE LOGITS
     Office
    0.90
     Commissioners
    0.84
     Representatives
    0.82
     Appropriations
    0.78
     Digest
    0.73
     Speaker
    0.73
     Correspond
    0.72
     Conference
    0.71
    OTUS
    0.71
    mith
    0.70
    Activations Density 0.019%

    No Known Activations