© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 2292
    Prev
    Next
    INDEX
    Explanations

    words related to physical journeys or trips

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    references to various types of journeys

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Mub
    -0.66
     Rowe
    -0.64
     Cust
    -0.62
     Entity
    -0.58
     Krug
    -0.57
     Amend
    -0.57
    holders
    -0.56
    ahoo
    -0.56
    rish
    -0.56
     Instr
    -0.56
    POSITIVE LOGITS
     home
    1.11
     toward
    1.00
    home
    0.97
     towards
    0.97
     downhill
    0.94
     into
    0.93
     down
    0.93
     downwards
    0.93
    through
    0.90
     forward
    0.90
    Activations Density 0.132%

    No Known Activations