© 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. 9-RES-JB
    11. 10261
    Prev
    Next
    INDEX
    Explanations

    phrases describing how well something fits a particular role or description

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate suitability or fitting within various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     fumble
    -0.68
     withheld
    -0.68
     wrest
    -0.65
     Appears
    -0.64
    ewitness
    -0.64
    ilee
    -0.62
    forced
    -0.61
    icides
    -0.61
     refusing
    -0.60
     consulted
    -0.59
    POSITIVE LOGITS
     criteria
    1.02
     mold
    0.98
     description
    0.97
     stereotype
    0.97
     neatly
    0.96
     precon
    0.96
     archetype
    0.94
    ahime
    0.92
     mould
    0.92
     nicely
    0.88
    Activations Density 0.200%

    No Known Activations