© 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. 8-RES-JB
    11. 14365
    Prev
    Next
    INDEX
    Explanations

    instructions or descriptions related to orientation and direction

    oai_token-act-pair · gpt-3.5-turbo

    references to directions and orientations

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    akings
    -0.73
    Rum
    -0.72
     Soup
    -0.72
     Reloaded
    -0.67
     confessions
    -0.67
     Flavoring
    -0.66
     Lemon
    -0.66
     Diesel
    -0.65
     Weekend
    -0.65
    OUP
    -0.65
    POSITIVE LOGITS
     perpendicular
    1.54
     downwards
    1.31
     angled
    1.28
     horizontal
    1.24
     perpend
    1.22
     direction
    1.21
     downward
    1.20
     horizontally
    1.18
     axis
    1.18
     vertical
    1.16
    Activations Density 0.671%

    No Known Activations