© 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. 18940
    Prev
    Next
    INDEX
    Explanations

    code snippets with for loops

    oai_token-act-pair · gpt-3.5-turbo

    programming structures and syntax in code

    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
    urized
    -0.70
    obal
    -0.64
     Shame
    -0.61
    FACE
    -0.61
    atory
    -0.61
     Accessed
    -0.60
    Press
    -0.59
     Copyright
    -0.59
    forth
    -0.58
    FUL
    -0.58
    POSITIVE LOGITS
     seq
    0.74
    index
    0.72
    slice
    0.70
    length
    0.68
    each
    0.66
    ){
    0.66
    artment
    0.65
     enumer
    0.65
     len
    0.65
    items
    0.64
    Activations Density 0.065%

    No Known Activations