© 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. 12853
    Prev
    Next
    INDEX
    Explanations

    phrases expressing a concept of truth or similarity between different situations

    oai_token-act-pair · gpt-3.5-turbo

    assertions of similarity or truth across different subjects or situations

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     Peb
    -0.55
    ++++++++++++++++
    -0.55
     ILCS
    -0.55
     Bones
    -0.54
    ahime
    -0.54
     Slim
    -0.53
    ct
    -0.52
     Encyclopedia
    -0.51
     contrace
    -0.51
    ographs
    -0.51
    POSITIVE LOGITS
     applies
    1.13
     apply
    1.06
     applied
    0.86
     happ
    0.73
     happening
    0.72
     true
    0.72
     applicable
    0.72
     prev
    0.70
    ativity
    0.68
    ALSE
    0.68
    Activations Density 0.179%

    No Known Activations