© 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. 10-RES-JB
    11. 24288
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

    oai_token-act-pair · gpt-3.5-turbo

    programming constructs related to function definitions and declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.92
    abouts
    -0.84
    bots
    -0.82
    kefeller
    -0.76
    otin
    -0.75
    yles
    -0.74
    agall
    -0.73
    united
    -0.72
    orne
    -0.72
    intensive
    -0.71
    POSITIVE LOGITS
    []
    0.98
     args
    0.91
     tmp
    0.89
     buf
    0.87
     []
    0.87
     msg
    0.86
     arg
    0.85
     num
    0.84
     sender
    0.83
     param
    0.81
    Activations Density 0.059%

    No Known Activations