© 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. 11-RES-JB
    11. 12941
    Prev
    Next
    INDEX
    Explanations

    text related to carbon cycle and energy usage

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases indicating connection or association between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Was
    -0.78
    tains
    -0.77
    was
    -0.76
     WAS
    -0.72
    laughs
    -0.69
    Was
    -0.69
    igr
    -0.66
     Himself
    -0.65
     herself
    -0.65
    arts
    -0.64
    POSITIVE LOGITS
     are
    1.68
     aren
    1.54
     were
    1.28
     have
    1.28
     deserve
    1.26
     weren
    1.20
    're
    1.19
     ARE
    1.18
     require
    1.17
     constitute
    1.16
    Activations Density 0.513%

    No Known Activations