© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 23315
    Prev
    Next
    INDEX
    Explanations

    names of celebrities or famous figures

    oai_token-act-pair · gpt-3.5-turbo

    names of notable people and organizations

    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
     guiActive
    -0.49
    ãĤ°
    -0.47
    yss
    -0.47
    ologically
    -0.47
    hematically
    -0.46
    early
    -0.46
    iman
    -0.45
    izont
    -0.45
    20439
    -0.44
    Instead
    -0.44
    POSITIVE LOGITS
     respectively
    1.05
    *.
    0.98
    +.
    0.97
    .
    0.89
    !.
    0.84
    .(
    0.83
     attRot
    0.82
    .).
    0.81
    .*
    0.80
    .–
    0.80
    Activations Density 1.008%

    No Known Activations