© 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. 22497
    Prev
    Next
    INDEX
    Explanations

    legal terms or concepts related to treaties, cases, and scandals

    oai_token-act-pair · gpt-3.5-turbo

    references to legal disputes and controversies

    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
    asus
    -0.61
    Tur
    -0.59
    ENTS
    -0.56
     NX
    -0.55
    scape
    -0.54
     Forestry
    -0.54
    BI
    -0.53
    ESA
    -0.52
    shield
    -0.52
     population
    -0.52
    POSITIVE LOGITS
    uggest
    1.43
    hips
    1.42
    ettings
    1.35
    hip
    1.32
    mith
    1.25
    paces
    1.24
    poons
    1.22
    hops
    1.20
    chool
    1.17
    cale
    1.13
    Activations Density 0.319%

    No Known Activations