© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 13110
    Prev
    Next
    INDEX
    Explanations

    mentions of government departments, particularly focusing on the Interior Department

    oai_token-act-pair · gpt-3.5-turbo

    references to the Interior Department and related governmental entities

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

    No Comments

    Negative Logits
    fortune
    -0.80
    fleet
    -0.77
    chers
    -0.76
    ppa
    -0.74
    KING
    -0.74
    urai
    -0.74
    amins
    -0.73
    onsense
    -0.73
    colo
    -0.72
    cible
    -0.70
    POSITIVE LOGITS
     ministry
    0.99
     Ministry
    0.94
     Interior
    0.88
     minister
    0.86
     Minister
    0.84
     Department
    0.79
     Affairs
    0.78
     Institution
    0.76
     Secretary
    0.76
     departments
    0.72
    Activations Density 0.012%

    No Known Activations