Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 10099
    Prev
    Next
    INDEX
    Explanations

    mentions of legal actions, specifically the act of sentencing individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to legal sentencing processes

    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
     UNESCO
    -0.75
    ijk
    -0.74
     Pixie
    -0.71
    Bus
    -0.71
    chu
    -0.71
    poll
    -0.68
    chrom
    -0.67
    wig
    -0.66
    walker
    -0.65
    ija
    -0.65
    POSITIVE LOGITS
     sentencing
    1.31
     sentenced
    0.94
     punishments
    0.94
     penalties
    0.90
     sanction
    0.86
    avorite
    0.86
     tyr
    0.85
     rulings
    0.84
     judgments
    0.84
     judgement
    0.84
    Activations Density 0.005%

    No Known Activations