© 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. 20474
    Prev
    Next
    INDEX
    Explanations

    specific details or information within the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of details or specifics regarding various topics

    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
    igham
    -0.69
    onz
    -0.65
    heid
    -0.65
    inals
    -0.65
    asca
    -0.64
    ammers
    -0.64
    sburgh
    -0.62
    rade
    -0.62
    asus
    -0.62
    opes
    -0.60
    POSITIVE LOGITS
     surrounding
    1.13
     about
    1.11
     regarding
    1.01
     redacted
    0.97
     thereof
    0.97
     pertaining
    0.94
     glean
    0.93
     concerning
    0.92
     of
    0.87
     details
    0.84
    Activations Density 0.083%

    No Known Activations