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. 10-RES-JB
    6. 11815
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures or positions related to the role of Secretary of State

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases that indicate positions or titles related to government officials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NetMessage
    -0.75
     traces
    -0.69
    rawdownloadcloneembedreportprint
    -0.60
     fatal
    -0.59
     scenarios
    -0.59
     hots
    -0.59
     od
    -0.58
     foul
    -0.57
     disadvantages
    -0.56
     injust
    -0.56
    POSITIVE LOGITS
     State
    1.09
     Commerce
    1.01
     Agriculture
    0.96
    ĺħ
    0.96
    State
    0.90
    state
    0.90
     Treasury
    0.88
     STATE
    0.87
     Transportation
    0.87
     Defense
    0.86
    Activations Density 0.020%

    No Known Activations