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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6-RES-JB
    11. 13493
    Prev
    Next
    INDEX
    Explanations

    financial terms and country-related information

    oai_token-act-pair · gpt-3.5-turbo

    sentences that mention the United States

    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
    bably
    -0.91
    ãĥł
    -0.72
    igs
    -0.69
    criptions
    -0.67
    lessly
    -0.66
     guiActiveUn
    -0.65
    ients
    -0.65
    ãĥŀ
    -0.64
    storms
    -0.64
    lets
    -0.63
    POSITIVE LOGITS
     Embassy
    1.07
     Postal
    1.06
     Treasury
    0.92
     embassy
    0.92
     Geological
    0.90
     Navy
    0.89
     Senate
    0.88
     Territories
    0.87
     Citizenship
    0.86
     Ambassador
    0.83
    Activations Density 0.055%

    No Known Activations