© 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. 14314
    Prev
    Next
    INDEX
    Explanations

    adjectives related to steepness

    oai_token-act-pair · gpt-3.5-turbo

    references to steepness or difficulty, particularly in physical or metaphorical contexts

    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
    ubb
    -0.82
    ignty
    -0.82
    uve
    -0.74
     Machina
    -0.72
    ©¶æ
    -0.67
    aurus
    -0.66
     Scotia
    -0.64
     Smy
    -0.63
    bers
    -0.62
    issors
    -0.60
    POSITIVE LOGITS
    ened
    1.09
    ening
    0.96
    ly
    0.95
     slope
    0.94
     slopes
    0.92
     uphill
    0.92
    ed
    0.90
     climb
    0.88
     gradient
    0.85
    est
    0.84
    Activations Density 0.022%

    No Known Activations