© 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. 7-RES-JB
    11. 14247
    Prev
    Next
    INDEX
    Explanations

    references to directions or spatial relationships, specifically focusing on the concept of 'the other way'

    oai_token-act-pair · gpt-3.5-turbo

    the term "other" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    zon
    -0.73
    _-
    -0.66
     1915
    -0.65
    aram
    -0.64
     Retrieved
    -0.64
    iste
    -0.63
    ãĥĥ
    -0.63
    theless
    -0.63
    ensibly
    -0.62
    iku
    -0.61
    POSITIVE LOGITS
    worldly
    1.75
     side
    1.03
     hemisphere
    0.83
    quickShipAvailable
    0.79
     thing
    0.77
    most
    0.73
     senses
    0.73
    world
    0.72
     direction
    0.71
     major
    0.70
    Activations Density 0.048%

    No Known Activations