© 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. 7-RES-JB
    11. 14218
    Prev
    Next
    INDEX
    Explanations

    references to the "Star Wars" franchise

    oai_token-act-pair · gpt-3.5-turbo

    references to pop culture, specifically movies and major franchises, along with geographical and statistical information

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     asses
    -0.71
     its
    -0.69
     compliant
    -0.65
     guideline
    -0.63
     cohesive
    -0.62
     resolve
    -0.61
     divided
    -0.59
     varied
    -0.58
     format
    -0.58
     rev
    -0.57
    POSITIVE LOGITS
    jon
    0.82
    çĶ°
    0.82
    Assistant
    0.77
    itars
    0.74
    oulder
    0.72
     pseudonym
    0.72
     Photographer
    0.69
    ragon
    0.69
    ocene
    0.69
    reprene
    0.69
    Activations Density 0.684%

    No Known Activations