© 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. 6315
    Prev
    Next
    INDEX
    Explanations

    words related to modes of transportation and travel

    oai_token-act-pair · gpt-3.5-turbo

    references to modes of travel

    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
    hemy
    -0.72
    thouse
    -0.71
    âķIJ
    -0.71
    urities
    -0.71
     shareholders
    -0.70
     ingred
    -0.69
    terness
    -0.67
    amental
    -0.64
    corn
    -0.64
    oldemort
    -0.62
    POSITIVE LOGITS
     canoe
    1.29
     pilgr
    1.28
     itiner
    1.15
     pilgrimage
    1.14
     trek
    1.12
     caravan
    1.12
     convoy
    1.09
     ferry
    1.08
     voyage
    1.07
     traveller
    1.06
    Activations Density 0.795%

    No Known Activations