© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 5991
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving addition or multiplication

    oai_token-act-pair · gpt-3.5-turbo

    mathematical expressions and operations in a technical context

    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
     Roads
    -0.61
     calendars
    -0.56
    erto
    -0.56
    bats
    -0.54
     seminars
    -0.53
     behavi
    -0.53
     acad
    -0.52
     committees
    -0.51
    BG
    -0.50
     corridors
    -0.50
    POSITIVE LOGITS
     ?)
    0.79
    ½
    0.76
    Ïī
    0.74
    )\
    0.69
    \)
    0.68
    ^{
    0.66
    +)
    0.66
    )/
    0.66
    )=(
    0.64
    ]+
    0.64
    Activations Density 0.094%

    No Known Activations