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. 16622
    Prev
    Next
    INDEX
    Explanations

    phrases related to the Department of Homeland Security

    oai_token-act-pair · gpt-3.5-turbo

    references to the Department of 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
    ISTER
    -0.70
    代
    -0.68
    leys
    -0.66
    ãģ®é
    -0.65
     gou
    -0.63
    venants
    -0.63
     unsub
    -0.63
    orem
    -0.62
    ðĿ
    -0.62
    apa
    -0.61
    POSITIVE LOGITS
     Security
    1.02
    security
    0.95
     security
    0.91
    istan
    0.86
     Defense
    0.81
     Homeland
    0.80
    elligence
    0.79
     Terror
    0.76
     Investigations
    0.76
     Identification
    0.75
    Activations Density 0.022%

    No Known Activations