© 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. 4-RES-JB
    11. 22132
    Prev
    Next
    INDEX
    Explanations

    keywords related to specialized units in law enforcement or investigations

    oai_token-act-pair · gpt-3.5-turbo

    references to various specialized units or task forces within organizations or agencies

    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
     straw
    -0.78
    vous
    -0.71
    issance
    -0.68
    nces
    -0.66
     fals
    -0.64
     Franch
    -0.63
    çĶŁ
    -0.62
    fter
    -0.61
    éĽ
    -0.61
    aukee
    -0.61
    POSITIVE LOGITS
    ary
    1.01
    mates
    0.95
    arily
    0.93
    mate
    0.93
    rity
    0.89
    aris
    0.87
     units
    0.81
    ARI
    0.81
    aries
    0.81
     unit
    0.80
    Activations Density 0.012%

    No Known Activations