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. 18376
    Prev
    Next
    INDEX
    Explanations

    government-related entities and legal terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of government entities and their officials

    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
     hitch
    -0.80
     leaps
    -0.75
     selfies
    -0.75
     warp
    -0.74
     surfing
    -0.73
     jog
    -0.72
     thrill
    -0.71
     piss
    -0.70
     Zionism
    -0.69
     triv
    -0.68
    POSITIVE LOGITS
    Department
    1.23
    ship
    1.15
    office
    1.08
    vernment
    1.08
    Commission
    1.05
    Executive
    1.02
    statement
    1.02
    Office
    1.01
    administ
    1.00
    minist
    1.00
    Activations Density 0.179%

    No Known Activations