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. 11-RES-JB
    6. 4019
    Prev
    Next
    INDEX
    Explanations

    specific mentions of people and their roles or actions within a context of legal or investigative occurrences

    oai_token-act-pair · gpt-3.5-turbo

    references to law enforcement and legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Brexit
    -0.81
    apest
    -0.79
     realise
    -0.75
     whilst
    -0.75
     Whilst
    -0.74
    inational
    -0.73
     beautifully
    -0.72
     ®
    -0.72
     realised
    -0.72
     queues
    -0.71
    POSITIVE LOGITS
     deputies
    1.17
     probation
    1.17
     detectives
    1.15
     sheriff
    1.14
     attorneys
    1.13
     prosecutors
    1.11
     defendants
    1.10
     juveniles
    1.09
     supervisors
    1.05
     county
    1.05
    Activations Density 0.409%

    No Known Activations