© 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. 11-RES-JB
    11. 22662
    Prev
    Next
    INDEX
    Explanations

    phrases related to illegal or inappropriate behavior involving minors

    oai_token-act-pair · gpt-3.5-turbo

    references to legal charges and incidents involving criminal behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Congratulations
    -0.81
    Ħ¢
    -0.74
    Reviewer
    -0.72
    大
    -0.71
    joice
    -0.71
     rejoice
    -0.71
    icult
    -0.70
    Flags
    -0.69
    oil
    -0.68
    roo
    -0.67
    POSITIVE LOGITS
     allegedly
    0.97
     sometime
    0.93
     Feb
    0.91
     totaling
    0.91
     Aug
    0.88
     Sept
    0.87
     consensual
    0.85
     inappropriately
    0.84
     sexually
    0.84
     Craigslist
    0.82
    Activations Density 0.539%

    No Known Activations