© 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. 1313
    Prev
    Next
    INDEX
    Explanations

    phrases related to instructional or tutorial content

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" in various contexts

    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
    /
    -0.87
    Whether
    -0.81
    îĢ
    -0.74
    Bloomberg
    -0.73
    ,''
    -0.73
    Govern
    -0.71
    Perhaps
    -0.71
    SHARE
    -0.70
    âĢł
    -0.69
    gov
    -0.69
    POSITIVE LOGITS
     rest
    1.11
     tutorial
    1.09
     pics
    1.07
     remainder
    0.99
     whole
    0.99
     basics
    0.97
     actual
    0.92
    ses
    0.92
     originals
    0.92
     english
    0.91
    Activations Density 0.329%

    No Known Activations