© 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. 4844
    Prev
    Next
    INDEX
    Explanations

    C++ programming code, including variable declarations, loops, functions, and syntax elements

    oai_token-act-pair · gpt-3.5-turbo

    code-related terms and syntax elements

    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
    ĸļ
    -0.84
    bots
    -0.78
    speak
    -0.76
    demon
    -0.73
    bourg
    -0.73
    leigh
    -0.73
    tan
    -0.71
    æĪ¦
    -0.71
    alia
    -0.70
    bell
    -0.70
    POSITIVE LOGITS
     args
    1.11
     tmp
    1.04
     buf
    1.02
     obj
    0.99
     msg
    0.97
     arg
    0.97
     addr
    0.96
     ptr
    0.95
     num
    0.93
     temp
    0.92
    Activations Density 0.060%

    No Known Activations