© 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. 9-RES-JB
    11. 10251
    Prev
    Next
    INDEX
    Explanations

    phrases related to public opinions and reactions

    oai_token-act-pair · gpt-3.5-turbo

    discussions related to societal issues and perceptions of privilege

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     nonetheless
    -0.78
    etheless
    -0.75
    utsche
    -0.71
     acknowledgment
    -0.69
     acknowledgement
    -0.68
     acknowledges
    -0.67
    »Ĵ
    -0.64
     Regions
    -0.64
    VICE
    -0.62
     Ezek
    -0.61
    POSITIVE LOGITS
     unbeat
    0.90
     boring
    0.88
     \"
    0.86
     inferior
    0.82
     crazy
    0.80
     invincible
    0.79
     unfairly
    0.79
     retarded
    0.78
     underrated
    0.78
     bad
    0.76
    Activations Density 0.618%

    No Known Activations