© 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. 11-RES-JB
    11. 14428
    Prev
    Next
    INDEX
    Explanations

    code snippets containing variable declarations and operations

    oai_token-act-pair · gpt-3.5-turbo

    references to programming concepts and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĢı
    -0.76
    /
    -0.73
    .","
    -0.71
     demol
    -0.68
     shading
    -0.65
    ".[
    -0.65
    conservancy
    -0.65
    "-
    -0.63
    ''.
    -0.62
     Helsinki
    -0.61
    POSITIVE LOGITS
     =
    1.20
    Args
    1.15
    Obj
    1.11
    Num
    1.06
    Name
    1.06
    Names
    1.03
    Len
    1.02
    Pos
    1.01
    Filename
    1.01
    Length
    1.00
    Activations Density 0.095%

    No Known Activations