© 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. 12-RES-JB
    11. 2276
    Prev
    Next
    INDEX
    Explanations

    references to video games and technology aspects

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    phrases associated with critique and observation of media portrayals

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    frey
    -0.75
    illion
    -0.74
    uncture
    -0.70
    iband
    -0.69
    UV
    -0.68
     obliged
    -0.66
     Accessed
    -0.66
    isin
    -0.66
    FTWARE
    -0.64
    rection
    -0.63
    POSITIVE LOGITS
     rest
    1.41
     others
    1.27
     originals
    1.25
     ones
    1.05
     usual
    1.03
     previous
    1.03
     norm
    1.02
     Others
    1.00
     likes
    0.96
     preceding
    0.96
    Activations Density 0.336%

    No Known Activations