© 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. 9-RES-JB
    11. 7070
    Prev
    Next
    INDEX
    Explanations

    legal terms related to criminal charges

    oai_token-act-pair · gpt-3.5-turbo

    references to legal charges and criminal offenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     optim
    -0.78
    ysc
    -0.73
     consulted
    -0.72
     ze
    -0.72
     pessim
    -0.68
    Opt
    -0.65
    matic
    -0.64
     favoured
    -0.64
     Jagu
    -0.64
    Reply
    -0.64
    POSITIVE LOGITS
     felony
    1.75
     misdemeanor
    1.69
     misdem
    1.38
     manslaughter
    1.37
     aggravated
    1.35
     burglary
    1.32
     charges
    1.29
    Charges
    1.28
     disorderly
    1.27
     felon
    1.26
    Activations Density 0.646%

    No Known Activations