© 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. 20404
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a requirement or condition for something to happen

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a purpose or intent behind actions

    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
    tex
    -0.73
    oat
    -0.72
    eworld
    -0.71
    odd
    -0.69
    redited
    -0.68
    irted
    -0.68
    tops
    -0.68
    ider
    -0.66
    inav
    -0.65
    sav
    -0.65
    POSITIVE LOGITS
     Osw
    0.90
    lies
    0.74
     financing
    0.69
    liness
    0.65
    aration
    0.64
     guaranteeing
    0.63
     fulfillment
    0.63
    meal
    0.63
    Ł
    0.62
     bolster
    0.61
    Activations Density 0.027%

    No Known Activations