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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 3670
    Prev
    Next
    INDEX
    Explanations

    phrases related to the U.S. House of Representatives

    oai_token-act-pair · gpt-3.5-turbo

    references to the U.S. House of Representatives

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

    No Comments

    Negative Logits
    istically
    -0.90
    ãĤ¨ãĥ«
    -0.89
    istic
    -0.82
    zsche
    -0.69
    company
    -0.68
    other
    -0.67
    illas
    -0.65
    istical
    -0.64
    isk
    -0.63
     Schl
    -0.62
    POSITIVE LOGITS
     Representatives
    1.05
     Speaker
    0.98
    hips
    0.91
     Appropriations
    0.90
    ricting
    0.82
    OTUS
    0.82
    woman
    0.78
    hip
    0.77
    mith
    0.77
     Representative
    0.76
    Activations Density 0.014%

    No Known Activations