© 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. 1-RES-JB
    11. 20530
    Prev
    Next
    INDEX
    Explanations

    words related to precision or correctness

    oai_token-act-pair · gpt-3.5-turbo

    references to accuracy and its evaluation in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    sg
    -0.84
     Pharma
    -0.76
    si
    -0.75
    ÃŁ
    -0.74
    hibit
    -0.74
     Towns
    -0.73
    Ing
    -0.72
    Bi
    -0.71
    joining
    -0.70
    Vert
    -0.70
    POSITIVE LOGITS
    uracy
    1.59
     accuracy
    1.39
     inacc
    1.36
     accur
    1.12
     mathemat
    1.09
     confir
    1.06
     inaccur
    1.03
     inaccurate
    1.00
     guiActiveUn
    0.98
     Accuracy
    0.98
    Activations Density 0.010%

    No Known Activations