Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 17992
    Prev
    Next
    INDEX
    Explanations

    words related to the Department of Homeland Security

    oai_token-act-pair · gpt-3.5-turbo

    references to "Homeland Security."

    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
    ãĤ¨ãĥ«
    -0.92
    ãĥĥãĤ¯
    -0.79
    ãĥ£
    -0.70
    juries
    -0.69
    cause
    -0.69
    isted
    -0.68
    amaz
    -0.68
    ãĥ¬
    -0.67
    stantial
    -0.67
    cipled
    -0.67
    POSITIVE LOGITS
     Investigations
    1.03
     Advis
    1.03
     Administration
    0.96
     Adviser
    0.96
     Advisor
    0.95
     Assistance
    0.89
     Security
    0.89
     Agency
    0.87
     Patrol
    0.87
     Oversight
    0.86
    Activations Density 0.011%

    No Known Activations