© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 9057
    Prev
    Next
    INDEX
    Explanations

    words related to legal judgments or decisions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to judicial decisions or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dak
    -0.71
    ffe
    -0.71
     Heritage
    -0.71
    ucket
    -0.65
     Adventures
    -0.63
    lde
    -0.63
    Bus
    -0.62
    access
    -0.61
     Tik
    -0.60
     Nun
    -0.59
    POSITIVE LOGITS
     verdict
    1.38
    ysis
    0.91
     judgment
    0.90
     judgement
    0.89
    naire
    0.85
     judgments
    0.81
     Judgment
    0.80
     conclud
    0.78
    iction
    0.75
    iseum
    0.75
    Activations Density 0.006%

    No Known Activations