© 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. 21939
    Prev
    Next
    INDEX
    Explanations

    text related to program execution and language syntax

    oai_token-act-pair · gpt-3.5-turbo

    non-text elements or sections of text that are not directly related to the content, such as text placeholders or formatting markers

    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
    edin
    -0.57
    mare
    -0.52
    å£
    -0.51
    BM
    -0.50
    âĢķ
    -0.50
    —-
    -0.48
    —
    -0.47
    rained
    -0.47
    ——
    -0.47
    busters
    -0.47
    POSITIVE LOGITS
    bidden
    0.92
    geries
    0.80
    gotten
    0.76
    instance
    0.71
    gettable
    0.70
    gery
    0.70
     instance
    0.70
     example
    0.68
     %%
    0.68
     linux
    0.67
    Activations Density 0.049%

    No Known Activations