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. 8147
    Prev
    Next
    INDEX
    Explanations

    phrases related to protest activities

    oai_token-act-pair · gpt-3.5-turbo

    references to protests and demonstrations

    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
    ucket
    -0.69
    neau
    -0.69
    availability
    -0.68
     TTL
    -0.68
    folio
    -0.67
    kj
    -0.66
    erion
    -0.66
     Pwr
    -0.66
    irements
    -0.66
    Reviewer
    -0.65
    POSITIVE LOGITS
     slogans
    1.51
     chanted
    1.18
     chants
    1.12
     chanting
    1.12
     denouncing
    0.98
     slogan
    0.97
     patriotic
    0.94
     chant
    0.94
     "#
    0.93
     protesting
    0.90
    Activations Density 0.168%

    No Known Activations