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. 7-RES-JB
    6. 16199
    Prev
    Next
    INDEX
    Explanations

    phrases related to military and defense activities

    oai_token-act-pair · gpt-3.5-turbo

    references to defense-related topics and officials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hell
    -0.78
    olics
    -0.70
    bern
    -0.68
    pel
    -0.66
    hest
    -0.65
    otin
    -0.65
    à
    -0.65
    upper
    -0.64
    heet
    -0.63
    colo
    -0.62
    POSITIVE LOGITS
     contractor
    1.02
     contractors
    0.89
     Secretary
    0.84
     Department
    0.83
     Ministry
    0.82
     ministry
    0.82
     Memor
    0.81
     Dept
    0.80
     Defense
    0.79
     Forces
    0.79
    Activations Density 0.022%

    No Known Activations