© 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. 0-RES-JB
    11. 1407
    Prev
    Next
    INDEX
    Explanations

    words related to computer programming and technology, particularly terms like "COM" and "IDE"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "COM" and related abbreviations or terms

    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
    arten
    -0.76
    atan
    -0.74
     Pillar
    -0.74
     Upton
    -0.69
    eed
    -0.68
    croft
    -0.68
    ually
    -0.68
    olds
    -0.67
     Norn
    -0.67
    aea
    -0.66
    POSITIVE LOGITS
     COM
    3.56
     IDE
    1.44
     CLS
    1.24
     MOV
    1.24
     CAN
    1.19
     CAS
    1.18
     SER
    1.17
     NET
    1.17
     COMM
    1.16
     ENTER
    1.09
    Activations Density 0.031%

    No Known Activations