© 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. 4-RES-JB
    11. 20759
    Prev
    Next
    INDEX
    Explanations

    keywords related to academic fields, such as "Computer Science" and "Political Science"

    oai_token-act-pair · gpt-3.5-turbo

    references to academic fields, particularly in science and engineering

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

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.77
    thumbnails
    -0.75
    alogue
    -0.73
    uders
    -0.68
    otte
    -0.68
    arranted
    -0.68
    20439
    -0.65
     predetermined
    -0.65
    UTC
    -0.65
    ULE
    -0.65
    POSITIVE LOGITS
     sciences
    0.99
     graduate
    0.88
     arts
    0.87
    chool
    0.84
    graduate
    0.84
    college
    0.82
     faculty
    0.81
     humanities
    0.81
    College
    0.81
     undergraduate
    0.81
    Activations Density 0.250%

    No Known Activations