© 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. 2431
    Prev
    Next
    INDEX
    Explanations

    instances of the word "back" with varying degrees of activation from 8 to 10

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

    instances related to the word "back."

    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
     regard
    -0.68
     unintended
    -0.60
     sudden
    -0.58
     Sorceress
    -0.58
     Scrolls
    -0.57
     background
    -0.55
     Strait
    -0.54
     misconception
    -0.54
     pall
    -0.54
     Verge
    -0.53
    POSITIVE LOGITS
    tracking
    1.31
    ped
    1.19
    packing
    1.17
    stab
    1.15
    dating
    1.01
    lit
    0.98
    ordered
    0.98
    dro
    0.97
    porting
    0.95
    ported
    0.94
    Activations Density 0.034%

    No Known Activations