© 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. 10-RES-JB
    11. 3165
    Prev
    Next
    INDEX
    Explanations

    criminal charges and legal terms

    oai_token-act-pair · gpt-3.5-turbo

    references to legal charges and crimes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pher
    -0.66
     goodbye
    -0.62
    Sov
    -0.61
     Sho
    -0.61
     Logo
    -0.60
    stra
    -0.60
    endi
    -0.60
     Slack
    -0.59
     sho
    -0.59
    opian
    -0.59
    POSITIVE LOGITS
    degree
    1.38
     felony
    1.12
     manslaughter
    1.04
     Degree
    1.04
     aggravated
    1.02
     misdemeanor
    0.95
     burglary
    0.95
     theft
    0.95
     punishable
    0.94
     degree
    0.93
    Activations Density 0.035%

    No Known Activations