© 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. 8-RES-JB
    6. 24059
    Prev
    Next
    INDEX
    Explanations

    phrases related to governmental organizations and funding

    oai_token-act-pair · gpt-3.5-turbo

    references to state and local government entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cellent
    -0.80
    ftime
    -0.79
    veyard
    -0.78
    nob
    -0.72
    uberty
    -0.71
    xual
    -0.70
    ocious
    -0.69
     Guilty
    -0.68
    gotten
    -0.68
    qq
    -0.67
    POSITIVE LOGITS
     governments
    1.22
     legislatures
    1.17
     mayors
    1.10
     districts
    1.07
     councils
    1.07
     jurisdictions
    1.07
     municipalities
    1.02
     departments
    1.00
     Governments
    0.97
    wide
    0.95
    Activations Density 0.195%

    No Known Activations