© 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. 7-RES-JB
    11. 3328
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal violations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal infractions and violations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tycoon
    -0.85
    arger
    -0.80
    roth
    -0.71
    reens
    -0.70
    trak
    -0.69
    NetMessage
    -0.68
    ilts
    -0.67
    opter
    -0.66
     bearded
    -0.66
    ointment
    -0.66
    POSITIVE LOGITS
     violations
    0.94
    viol
    0.85
     Viol
    0.79
     violation
    0.79
     infring
    0.75
    mson
    0.71
     Compliance
    0.71
     Behavior
    0.69
     punishable
    0.66
     Logged
    0.64
    Activations Density 0.027%

    No Known Activations