© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 23162
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or governmental committees

    oai_token-act-pair · gpt-3.5-turbo

    references to legislative committees and hearings

    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
     Pyr
    -0.77
    ku
    -0.76
    resp
    -0.75
    spr
    -0.72
     Barbar
    -0.71
     precip
    -0.67
    gra
    -0.64
    zsche
    -0.64
    rave
    -0.63
     Maid
    -0.62
    POSITIVE LOGITS
     hearings
    1.16
     recess
    1.01
    Senate
    1.00
     subcommittee
    0.98
    ittee
    0.97
     committees
    0.93
     Subcommittee
    0.91
     Hearing
    0.89
     chaired
    0.87
     chair
    0.87
    Activations Density 0.031%

    No Known Activations