© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 19308
    Prev
    Next
    INDEX
    Explanations

    terms related to occupation, particularly in a political or geographical context

    oai_token-act-pair · gpt-3.5-turbo

    terms related to occupation and occupancy

    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
    peer
    -0.75
    uber
    -0.73
    à¥
    -0.70
    raft
    -0.69
    ect
    -0.69
    irling
    -0.68
    bang
    -0.68
    brother
    -0.67
    nir
    -0.65
    Fly
    -0.65
    POSITIVE LOGITS
     Territories
    0.88
    ational
    0.85
     Territory
    0.81
     occupied
    0.78
     occupying
    0.75
     occupation
    0.75
     Borders
    0.74
     territories
    0.73
    iture
    0.68
     occup
    0.67
    Activations Density 0.040%

    No Known Activations