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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4651
    Prev
    Next
    INDEX
    Explanations

    phrases related to law enforcement agents

    oai_token-act-pair · gpt-3.5-turbo

    mentions of law enforcement or investigative agents

    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
    olon
    -0.69
    orthern
    -0.64
    unning
    -0.64
    aspberry
    -0.63
    numbered
    -0.63
    vre
    -0.63
    ustom
    -0.62
    utan
    -0.61
     Pew
    -0.61
    astery
    -0.60
    POSITIVE LOGITS
     agents
    4.01
     agent
    3.14
     Agents
    3.10
    agents
    2.70
     Agent
    2.48
    agent
    2.27
    Agent
    2.17
     operatives
    1.57
     informants
    1.49
     agencies
    1.49
    Activations Density 0.017%

    No Known Activations