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. 11-RES-JB
    6. 8756
    Prev
    Next
    INDEX
    Explanations

    government and administrative entities, particularly those related to law enforcement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to government and official organizations

    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
    ernels
    -0.83
    icides
    -0.82
    ittens
    -0.80
    bats
    -0.80
    names
    -0.79
    ults
    -0.79
    perors
    -0.78
    rencies
    -0.77
     Romans
    -0.77
    riages
    -0.76
    POSITIVE LOGITS
     spokesperson
    1.55
     spokeswoman
    1.52
     spokesman
    1.52
     staffer
    1.35
     representative
    1.25
     aide
    1.24
     official
    1.21
     insider
    1.14
     source
    1.14
     employee
    1.11
    Activations Density 0.159%

    No Known Activations