© 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. 14371
    Prev
    Next
    INDEX
    Explanations

    statements about social, economic, and political circumstances and trends

    oai_token-act-pair · gpt-3.5-turbo

    statements related to the current state of the economy and societal issues

    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
     Ends
    -0.76
    rarily
    -0.75
     Telesc
    -0.70
     Afterwards
    -0.68
     Benefits
    -0.67
     Towers
    -0.66
     Dress
    -0.65
     Telescope
    -0.65
     Oaks
    -0.65
     Edit
    -0.63
    POSITIVE LOGITS
     poised
    1.33
     gearing
    1.13
     accelerating
    1.09
     scrambling
    1.08
     slowing
    1.05
     eyeing
    1.05
     struggling
    1.04
     increasingly
    1.04
     preparing
    1.04
     shifting
    1.03
    Activations Density 0.507%

    No Known Activations