© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 16249
    Prev
    Next
    INDEX
    Explanations

    phrases related to political figures holding specific government positions

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "Secretary of State."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     traces
    -0.72
    NetMessage
    -0.70
     arteries
    -0.66
     schematic
    -0.64
     webcam
    -0.62
    rawdownloadcloneembedreportprint
    -0.62
     scenarios
    -0.61
     flared
    -0.61
     fatal
    -0.61
     hots
    -0.60
    POSITIVE LOGITS
     Commerce
    1.00
    ĺħ
    0.96
     Agriculture
    0.95
     State
    0.94
     Transportation
    0.92
     Treasury
    0.89
    ²¾
    0.88
     Homeland
    0.87
    Commerce
    0.87
     Defense
    0.83
    Activations Density 0.036%

    No Known Activations