© 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. 0-RES-JB
    11. 7700
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific place or location called "Hampstead."

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific location or establishment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ko
    -0.67
     Korean
    -0.64
    IZE
    -0.60
     Remy
    -0.60
     apologize
    -0.59
     racism
    -0.59
     Mi
    -0.59
     exam
    -0.59
     Xer
    -0.57
     URL
    -0.57
    POSITIVE LOGITS
    stead
    5.09
     Stead
    1.57
    sted
    1.45
    tons
    1.05
    solid
    0.99
     stead
    0.98
    ington
    0.97
    haven
    0.95
    slow
    0.94
    stad
    0.94
    Activations Density 0.007%

    No Known Activations