© 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. 12800
    Prev
    Next
    INDEX
    Explanations

    positive descriptions related to sports performance

    oai_token-act-pair · gpt-3.5-turbo

    sentences with strong concluding statements or punctuation

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     aborted
    -0.79
     erased
    -0.79
     extinguished
    -0.77
     censored
    -0.77
     reversed
    -0.76
     embargo
    -0.74
     contingency
    -0.74
     altered
    -0.73
     postponed
    -0.72
     legal
    -0.72
    POSITIVE LOGITS
     However
    1.23
     Highly
    1.21
     Whenever
    1.19
     His
    1.18
     Moreover
    1.15
     Plus
    1.15
     Unfortunately
    1.14
     Whether
    1.14
     Additionally
    1.14
     Occasionally
    1.14
    Activations Density 0.471%

    No Known Activations