© 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. 7-RES-JB
    11. 12586
    Prev
    Next
    INDEX
    Explanations

    terms related to geographical locations with the term "Greater" before the location name

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations or areas

    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
    ulating
    -0.98
    ulators
    -0.95
    ulates
    -0.95
    ulation
    -0.85
    ulatory
    -0.85
    ouses
    -0.85
    ulate
    -0.85
    ulated
    -0.85
    sters
    -0.81
    ulations
    -0.79
    POSITIVE LOGITS
     Territories
    0.90
     Than
    0.87
     Regional
    0.80
     Albania
    0.77
     Communities
    0.77
     Areas
    0.75
    burgh
    0.74
     Voices
    0.73
     eleph
    0.71
     Dir
    0.71
    Activations Density 0.050%

    No Known Activations