© 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. 8-RES-JB
    11. 6532
    Prev
    Next
    INDEX
    Explanations

    words related to legal actions, such as "rejected" and "petition."

    oai_token-act-pair · gpt-3.5-turbo

    instances of judicial decisions and court rulings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.82
    ombies
    -0.78
    ombat
    -0.78
    obyl
    -0.77
    ãĥŀ
    -0.73
    aucuses
    -0.70
    Ò
    -0.70
    peak
    -0.69
    qv
    -0.69
    Ranked
    -0.67
    POSITIVE LOGITS
     defendants
    1.07
     defendant
    1.02
     petitioner
    0.99
     injunction
    0.99
     plaintiffs
    0.98
     verdict
    0.97
     acqu
    0.95
     plaintiff
    0.93
     convict
    0.93
     prosecuting
    0.91
    Activations Density 0.365%

    No Known Activations