Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 17179
    Prev
    Next
    INDEX
    Explanations

    words related to physical crowd control methods or actions, such as tear gas, water cannons, rubber bullets, and pepper spray

    oai_token-act-pair · gpt-3.5-turbo

    terms related to riot control tactics and crowd management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Revel
    -0.79
     Wonderland
    -0.77
    BSD
    -0.76
     Passage
    -0.74
    Leary
    -0.73
    Dream
    -0.73
    Tax
    -0.72
    Ast
    -0.71
    Travel
    -0.70
    WR
    -0.69
    POSITIVE LOGITS
     grenades
    1.25
     grenade
    1.03
     spraying
    0.84
     Grenade
    0.82
     fired
    0.80
     disinfect
    0.80
     launchers
    0.79
     shields
    0.79
    asers
    0.77
     darts
    0.77
    Activations Density 0.085%

    No Known Activations