© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 12313
    Prev
    Next
    INDEX
    Explanations

    barcodes and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to coding and barcodes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pedest
    -0.68
     Shields
    -0.68
     sadd
    -0.64
     fellows
    -0.64
     Peterson
    -0.63
     aver
    -0.63
     depos
    -0.61
     concent
    -0.61
     purs
    -0.60
     hopes
    -0.60
    POSITIVE LOGITS
    code
    4.43
    codes
    3.68
    Code
    2.38
    coded
    2.23
     code
    2.05
     CODE
    1.88
     codes
    1.85
     Code
    1.82
     Codes
    1.65
    cod
    1.58
    Activations Density 0.013%

    No Known Activations