© 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. 10-RES-JB
    11. 13629
    Prev
    Next
    INDEX
    Explanations

    locations or places

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the location of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uploads
    -0.65
    show
    -0.63
    sen
    -0.61
    sequence
    -0.60
    ese
    -0.59
    ework
    -0.59
    doms
    -0.58
     diapers
    -0.57
    spir
    -0.56
    shows
    -0.56
    POSITIVE LOGITS
     atop
    1.08
     near
    1.07
    uate
    1.01
     smack
    0.98
     centrally
    0.97
     northwest
    0.96
     somewhere
    0.96
     southwest
    0.95
     adjacent
    0.95
     northeast
    0.94
    Activations Density 0.063%

    No Known Activations