© 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. 7-RES-JB
    11. 10974
    Prev
    Next
    INDEX
    Explanations

    references to legal opinions, judicial decisions, and legal terms

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal opinions and governmental authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lonely
    -0.84
     gobl
    -0.80
     highs
    -0.80
    icro
    -0.78
     flares
    -0.77
     Rune
    -0.77
     GMT
    -0.73
     Lanka
    -0.72
    ranean
    -0.72
     Jazeera
    -0.72
    POSITIVE LOGITS
     appellant
    1.47
     plaintiff
    1.47
     plaintiffs
    1.41
     Plaint
    1.39
     Plaintiff
    1.37
     defendant
    1.35
     Defendant
    1.33
     appellate
    1.31
     statute
    1.31
     petitioner
    1.26
    Activations Density 0.995%

    No Known Activations