© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7-RES-JB
    11. 14469
    Prev
    Next
    INDEX
    Explanations

    software programming terms and syntax

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     seismic
    -0.57
     substance
    -0.54
     contingency
    -0.53
     flavors
    -0.52
     clutter
    -0.49
     urgency
    -0.49
     avenues
    -0.47
     overload
    -0.47
     tumult
    -0.47
     seams
    -0.47
    POSITIVE LOGITS
    Jr
    0.75
    ij士
    0.73
    EStream
    0.62
    eus
    0.59
    $$$$
    0.58
    lda
    0.58
    âĨij
    0.58
    aeper
    0.57
    ÃĥÃĤ
    0.56
    )</
    0.56
    Activations Density 1.219%

    No Known Activations