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

    Neuronpedia

    APICircuit 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. 8-RES-JB
    6. 1387
    Prev
    Next
    INDEX
    Explanations

    people involved in legal or political actions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of independent politicians or activists facing consequences from the government

    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
     Purg
    -0.75
    reci
    -0.66
     sear
    -0.63
     Recovery
    -0.62
     Surviv
    -0.62
     whirlwind
    -0.59
     Horror
    -0.59
    imon
    -0.58
    ount
    -0.58
    Mem
    -0.58
    POSITIVE LOGITS
     transgress
    1.11
     tresp
    1.02
     violating
    0.98
     contra
    0.98
     dared
    0.98
     unlawfully
    0.95
     disobedience
    0.94
     violations
    0.93
     illegally
    0.93
     improperly
    0.92
    Activations Density 0.693%

    No Known Activations