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

    Neuronpedia

    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. 9458
    Prev
    Next
    INDEX
    Explanations

    mentions of locations or environments that are external to a specified context

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "outside."

    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
    ulous
    -0.78
    anche
    -0.78
    ander
    -0.72
    vous
    -0.71
    onder
    -0.69
    antine
    -0.69
    ulously
    -0.69
    oka
    -0.68
    ery
    -0.68
    ency
    -0.67
    POSITIVE LOGITS
     Borders
    0.75
     bounds
    0.74
     jurisdictions
    0.72
     Antarctica
    0.71
     observer
    0.68
    side
    0.67
     worlds
    0.67
    shock
    0.67
     academia
    0.66
    world
    0.65
    Activations Density 0.034%

    No Known Activations