© 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. 0-RES-JB
    11. 6690
    Prev
    Next
    INDEX
    Explanations

    keywords related to legal cases and law enforcement, specifically focusing on details from Fairfax County

    oai_token-act-pair · gpt-3.5-turbo

    references to Fairfax County

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ->
    -0.77
    oj
    -0.76
     monster
    -0.72
    ube
    -0.70
     monsters
    -0.69
     proteins
    -0.67
     protein
    -0.66
     axis
    -0.66
     pairing
    -0.65
    =>
    -0.63
    POSITIVE LOGITS
     Fairfax
    4.23
     Arlington
    1.69
    Fair
    1.67
    fax
    1.46
     Canberra
    1.38
     Newtown
    1.28
     Turnbull
    1.24
     Norfolk
    1.24
     Richmond
    1.23
     NBN
    1.23
    Activations Density 0.018%

    No Known Activations