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. 10-RES-JB
    6. 3716
    Prev
    Next
    INDEX
    Explanations

    phrases related to illegal activities and regulations

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to legality and regulation of substances and activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    angular
    -0.72
     Shards
    -0.69
    otta
    -0.68
    sum
    -0.68
    aldo
    -0.63
    dig
    -0.62
    twitch
    -0.62
    snap
    -0.62
    Completed
    -0.61
     teasp
    -0.61
    POSITIVE LOGITS
     lawfully
    1.46
     unlawfully
    1.44
     illegally
    1.41
     unregulated
    1.30
     violates
    1.25
     legally
    1.24
     unlawful
    1.22
     prohibited
    1.21
     violate
    1.19
     lawful
    1.14
    Activations Density 0.448%

    No Known Activations