© 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. 6-RES-JB
    11. 16859
    Prev
    Next
    INDEX
    Explanations

    details related to criminal activities and legal processes

    oai_token-act-pair · gpt-3.5-turbo

    actions depicting conflict or legal issues involving individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    selves
    -0.75
    âĢ¦)
    -0.70
     ourselves
    -0.69
    ]).
    -0.63
    }.
    -0.62
     theme
    -0.62
     ..."
    -0.61
    Japan
    -0.60
     Theme
    -0.60
     folks
    -0.60
    POSITIVE LOGITS
     aggravated
    0.87
     remorse
    0.86
     voluntarily
    0.79
     unsuccessfully
    0.77
     orally
    0.74
    Charges
    0.73
     burglary
    0.72
     arra
    0.70
     plead
    0.70
     testified
    0.70
    Activations Density 0.672%

    No Known Activations