© 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. 8-RES-JB
    11. 23819
    Prev
    Next
    INDEX
    Explanations

    references to legal or criminal charges

    oai_token-act-pair · gpt-3.5-turbo

    references to legal charges and related legal processes

    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
     livest
    -0.85
     nutrit
    -0.71
    skill
    -0.70
    ARCH
    -0.68
    issance
    -0.67
     contrace
    -0.67
     tastes
    -0.64
     tactile
    -0.64
     usability
    -0.63
     taste
    -0.63
    POSITIVE LOGITS
    heet
    1.31
     levied
    1.05
     punishable
    1.02
     charges
    0.95
     stemming
    0.94
     misdem
    0.93
     alleging
    0.91
     Charges
    0.90
     sheet
    0.90
     indicted
    0.89
    Activations Density 0.057%

    No Known Activations