© 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. 2297
    Prev
    Next
    INDEX
    Explanations

    comparisons related to performance or evaluation

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

    expressions related to improvement or better understanding

    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
    sbm
    -0.95
    packed
    -0.65
    xit
    -0.63
    Lago
    -0.62
    cedes
    -0.62
    ãĤ´ãĥ³
    -0.61
    jured
    -0.61
    tar
    -0.61
    raid
    -0.60
    ril
    -0.60
    POSITIVE LOGITS
     idea
    1.39
     sense
    1.21
     indication
    1.19
     ballpark
    1.19
     clue
    1.15
     grasp
    1.14
     approximation
    1.05
     clearer
    1.04
     impression
    1.04
     handle
    1.04
    Activations Density 0.230%

    No Known Activations