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. 21692
    Prev
    Next
    INDEX
    Explanations

    words related to military bases and locations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of military bases

    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
    Interstitial
    -0.82
    spir
    -0.80
    âĶģ
    -0.78
     Marketable
    -0.75
    chrom
    -0.74
    MpServer
    -0.73
     ILCS
    -0.72
    theless
    -0.70
    poll
    -0.69
    à¥
    -0.69
    POSITIVE LOGITS
    camp
    1.01
    anamo
    0.97
     garrison
    0.87
    pole
    0.85
     stationed
    0.83
     hangar
    0.81
     manned
    0.81
     chapel
    0.80
     barracks
    0.80
     Station
    0.78
    Activations Density 0.037%

    No Known Activations