© 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. 13085
    Prev
    Next
    INDEX
    Explanations

    instances where a specific action is recommended or suggested

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "to do so."

    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
     Lau
    -0.66
     Hunters
    -0.63
     Dreams
    -0.63
    Ĩ
    -0.62
    aughed
    -0.62
    works
    -0.59
    ²
    -0.59
    resa
    -0.58
    dust
    -0.58
     Picks
    -0.56
    POSITIVE LOGITS
    oner
    1.02
     anonymously
    0.90
    zin
    0.83
    othe
    0.83
     willingly
    0.83
     voluntarily
    0.82
     responsibly
    0.79
     cheaply
    0.79
     legally
    0.77
     reluctantly
    0.77
    Activations Density 0.020%

    No Known Activations