© 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. 13097
    Prev
    Next
    INDEX
    Explanations

    phrases comparing or contrasting two entities

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases indicating higher or lower values or conditions

    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
    zos
    -0.83
    istries
    -0.63
    izont
    -0.60
     Shelter
    -0.59
    LD
    -0.58
    bes
    -0.58
    vard
    -0.57
    vind
    -0.57
    GC
    -0.57
    nin
    -0.56
    POSITIVE LOGITS
     pesky
    1.00
     aforementioned
    0.84
     fateful
    0.72
    chers
    0.72
     elusive
    0.70
     same
    0.68
     describ
    0.68
     amount
    0.68
     dreaded
    0.67
     pertaining
    0.66
    Activations Density 0.168%

    No Known Activations