© 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. 3-RES-JB
    11. 23365
    Prev
    Next
    INDEX
    Explanations

    lines of code or programming-related text

    oai_token-act-pair · gpt-3.5-turbo

    programming-related syntax and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibaba
    -0.91
    ilial
    -0.84
    raq
    -0.83
    é¾
    -0.83
    utra
    -0.77
    ignty
    -0.76
    asca
    -0.76
     plots
    -0.72
    atre
    -0.72
    Ô
    -0.71
    POSITIVE LOGITS
     );
    0.89
     _
    0.80
     local
    0.80
     uint
    0.79
     fmt
    0.77
     null
    0.77
     sizeof
    0.76
     )
    0.76
     invalid
    0.74
     parent
    0.73
    Activations Density 0.132%

    No Known Activations