© 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. 11350
    Prev
    Next
    INDEX
    Explanations

    programming languages

    oai_token-act-pair · gpt-3.5-turbo

    references to programming and spoken languages

    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
    wire
    -0.72
     tank
    -0.70
    owner
    -0.66
    Wire
    -0.64
    invest
    -0.63
    apeake
    -0.63
    Tank
    -0.62
    care
    -0.62
    tank
    -0.62
     pump
    -0.60
    POSITIVE LOGITS
     languages
    3.86
     Languages
    3.28
    anguages
    2.30
     language
    2.23
     Language
    2.00
    language
    1.92
    Language
    1.90
     tongues
    1.69
     religions
    1.57
     currencies
    1.56
    Activations Density 0.012%

    No Known Activations