© 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. 6205
    Prev
    Next
    INDEX
    Explanations

    legal terms related to sentencing and imprisonment

    oai_token-act-pair · gpt-3.5-turbo

    information related to legal sentencing and court proceedings

    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
    Maps
    -0.96
    ãĤ¿
    -0.93
    âĹ¼
    -0.88
    Theme
    -0.81
    zinski
    -0.76
    amins
    -0.76
    Pinterest
    -0.75
    natureconservancy
    -0.75
    metry
    -0.74
    omorphic
    -0.74
    POSITIVE LOGITS
     parole
    1.24
     convicted
    1.24
     sentencing
    1.22
     Judge
    1.18
     acquitted
    1.16
     sentenced
    1.15
     prosecutors
    1.14
     probation
    1.13
     extradition
    1.11
    Judge
    1.10
    Activations Density 0.676%

    No Known Activations