© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 7046
    Prev
    Next
    INDEX
    Explanations

    phrases related to civil unrest and police actions

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of police actions and crowd control measures during protests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.90
     XY
    -0.83
     Lifetime
    -0.81
     greatness
    -0.75
     congr
    -0.72
     Tycoon
    -0.72
     deserves
    -0.70
    issance
    -0.69
    stellar
    -0.69
    uga
    -0.69
    POSITIVE LOGITS
     slogans
    1.06
     makeshift
    1.04
     tyres
    0.99
     demonstrators
    0.98
     barric
    0.98
     protesters
    0.98
     chanting
    0.93
     shouting
    0.89
     passers
    0.89
     militants
    0.87
    Activations Density 0.707%

    No Known Activations