Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 10642
    Prev
    Next
    INDEX
    Explanations

    words related to unethical, illegal, and criminal behavior

    oai_token-act-pair · gpt-3.5-turbo

    references to illegal or unethical actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ciation
    -0.85
    aber
    -0.82
    essim
    -0.80
    ãĥ´
    -0.80
    oreal
    -0.79
    ascript
    -0.78
    undrum
    -0.76
    ipeg
    -0.73
    Market
    -0.73
    igue
    -0.73
    POSITIVE LOGITS
     defendants
    1.13
     mishand
    1.10
     perpetrators
    1.06
     whistleblowers
    1.03
     contractor
    1.03
     disgr
    1.02
     whistleblower
    1.01
     whistlebl
    1.00
     contractors
    1.00
     dealings
    1.00
    Activations Density 0.666%

    No Known Activations