© 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. 0-RES-JB
    11. 5397
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal cases and proceedings

    oai_token-act-pair · gpt-3.5-turbo

    legal terms and phrases associated with the Supreme Court and judicial proceedings

    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
    ships
    -0.73
     STD
    -0.70
     Andromeda
    -0.67
    ILE
    -0.65
     darts
    -0.65
    stage
    -0.65
    CDC
    -0.65
     Carth
    -0.64
     Samoa
    -0.63
    STD
    -0.63
    POSITIVE LOGITS
     Hebdo
    1.55
     devote
    1.52
    reme
    1.40
     vigilant
    1.39
     thrill
    1.24
    jer
    1.22
    itement
    1.20
     Klux
    1.00
     Extrem
    0.99
     Tayyip
    0.96
    Activations Density 0.044%

    No Known Activations