© 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. 23277
    Prev
    Next
    INDEX
    Explanations

    snippets of computer programming code

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of code-related syntax or commands

    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
     citiz
    -0.73
     exting
    -0.64
     eleph
    -0.64
     proport
    -0.63
     pione
    -0.61
     newcom
    -0.60
     oun
    -0.59
     Courier
    -0.59
     newsp
    -0.59
    Þ
    -0.58
    POSITIVE LOGITS
    Notice
    0.88
    ↵
    0.86
    Alternatively
    0.82
    ³³³³³³³³³³³³³³³³
    0.81
    Then
    0.79
    Thus
    0.78
    ????????
    0.77
    ³³³
    0.76
    Clearly
    0.75
    Similarly
    0.75
    Activations Density 0.273%

    No Known Activations