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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2698
    Prev
    Next
    INDEX
    Explanations

    locations or places

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating physical locations

    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
    ework
    -0.84
    eries
    -0.78
    vous
    -0.77
    haw
    -0.72
    airs
    -0.72
    rendered
    -0.70
    eden
    -0.69
    nature
    -0.68
    ned
    -0.68
    ese
    -0.67
    POSITIVE LOGITS
    uate
    0.95
     downtown
    0.87
     atop
    0.85
     centrally
    0.85
     near
    0.85
     smack
    0.84
     geographically
    0.84
     somewhere
    0.83
     therein
    0.83
     inside
    0.80
    Activations Density 0.048%

    No Known Activations