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. 6-RES-JB
    6. 16380
    Prev
    Next
    INDEX
    Explanations

    mentions of the position of Secretary of State, particularly associated with Hillary Clinton and John Kerry

    oai_token-act-pair · gpt-3.5-turbo

    references to the role of Secretary of State

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     flashbacks
    -0.70
    aways
    -0.67
    NetMessage
    -0.66
     seams
    -0.63
     hots
    -0.63
     strips
    -0.62
     dots
    -0.62
    upon
    -0.61
     scenarios
    -0.60
     traces
    -0.60
    POSITIVE LOGITS
     Commerce
    0.82
     Communications
    0.82
     Agriculture
    0.76
     Treasury
    0.75
     Shipping
    0.73
     Transportation
    0.73
     Communication
    0.72
     Information
    0.71
    ĺħ
    0.71
    afort
    0.70
    Activations Density 0.044%

    No Known Activations