© 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. 14332
    Prev
    Next
    INDEX
    Explanations

    terms related to legal language

    oai_token-act-pair · gpt-3.5-turbo

    negative sentiments or expressions of disapproval

    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
     bere
    -0.63
     cir
    -0.61
     forth
    -0.58
     Learned
    -0.58
     divest
    -0.57
     incred
    -0.56
     cous
    -0.56
     NAS
    -0.56
    sson
    -0.55
     pract
    -0.55
    POSITIVE LOGITS
    shaped
    1.22
    series
    1.03
    dimensional
    0.97
    bomb
    0.95
    factor
    0.93
    Unit
    0.92
    level
    0.91
    word
    0.88
    sized
    0.87
    FU
    0.87
    Activations Density 0.050%

    No Known Activations