© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 19756
    Prev
    Next
    INDEX
    Explanations

    words related to protests and clashes with authorities

    oai_token-act-pair · gpt-3.5-turbo

    keywords associated with protests and demonstrations

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

    No Comments

    Negative Logits
     Inher
    -0.80
     theorem
    -0.77
     inher
    -0.77
    ministic
    -0.74
     probabilities
    -0.73
    fact
    -0.73
     resear
    -0.72
     mature
    -0.71
     matured
    -0.71
     Depend
    -0.68
    POSITIVE LOGITS
     protestors
    1.20
     protesters
    1.19
     chanting
    1.13
     barric
    1.09
     Protesters
    1.09
     protest
    1.08
     riot
    1.07
     demonstrators
    1.05
     protesting
    1.00
     Protest
    0.99
    Activations Density 0.829%

    No Known Activations