© 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. 11-RES-JB
    11. 12659
    Prev
    Next
    INDEX
    Explanations

    phrases related to spatial orientation and direction

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to spatial relationships and directions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.73
    GW
    -0.65
     Punk
    -0.63
    unker
    -0.63
    KS
    -0.62
     Heist
    -0.61
    cash
    -0.61
     outfits
    -0.61
    piracy
    -0.61
    criminal
    -0.60
    POSITIVE LOGITS
     perpendicular
    1.41
     perpend
    1.19
     axis
    1.18
     (=
    1.17
     horizontally
    1.11
     downwards
    1.10
     (-
    1.06
     (âĪĴ
    1.04
     direction
    1.01
     vertically
    1.00
    Activations Density 0.251%

    No Known Activations