© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20186
    Prev
    Next
    INDEX
    Explanations

    words related to legal violations

    oai_token-act-pair · gpt-3.5-turbo

    references to legal violations and infringements

    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
     Tycoon
    -0.83
    arger
    -0.81
    urai
    -0.68
    mad
    -0.68
    roth
    -0.67
    apult
    -0.66
     bearded
    -0.65
    wow
    -0.64
    anka
    -0.63
     consolation
    -0.63
    POSITIVE LOGITS
     violations
    0.96
    viol
    0.86
     violation
    0.80
     Viol
    0.71
    mson
    0.70
     Behavior
    0.70
     unfocusedRange
    0.68
     punishable
    0.67
     behaviors
    0.67
     infring
    0.67
    Activations Density 0.035%

    No Known Activations