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. 0-RES-JB
    6. 7035
    Prev
    Next
    INDEX
    Explanations

    words related to acts of protest

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "protest" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reditary
    -0.71
    irements
    -0.69
    »Ĵ
    -0.68
     Chips
    -0.68
     Flavoring
    -0.68
     Grimoire
    -0.67
    balanced
    -0.65
    ogg
    -0.65
     Lifetime
    -0.65
    icator
    -0.64
    POSITIVE LOGITS
     protest
    3.56
     protests
    2.48
     Protest
    2.46
     protesting
    2.29
     protested
    2.00
     protestors
    1.88
     protester
    1.84
     protesters
    1.81
     revolt
    1.68
     dissent
    1.65
    Activations Density 0.010%

    No Known Activations