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. 8-RES-JB
    6. 19995
    Prev
    Next
    INDEX
    Explanations

    descriptions of a specific setting involving monitoring rooms and military personnel

    oai_token-act-pair · gpt-3.5-turbo

    scenes involving military personnel or authority figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     taxpayer
    -0.76
     critics
    -0.75
     sensit
    -0.75
     taxpayers
    -0.67
     proven
    -0.67
     Tests
    -0.65
    ymes
    -0.64
     Tulsa
    -0.64
    Iowa
    -0.63
     Critics
    -0.63
    POSITIVE LOGITS
     beck
    0.97
     silhou
    0.94
    looking
    0.93
     indist
    0.92
     doorway
    0.89
    SCP
    0.85
     kneeling
    0.83
     protr
    0.83
     brightly
    0.82
    occupied
    0.81
    Activations Density 0.635%

    No Known Activations