© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5834
    Prev
    Next
    INDEX
    Explanations

    technology-related terms like "blockchain" and "update" as well as terms related to command-line instructions and file management

    oai_token-act-pair · gpt-3.5-turbo

    terms and references related to data processing and files

    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
     [âĢ¦]
    -0.66
    SPONSORED
    -0.65
     Beir
    -0.63
     nearer
    -0.59
     âĢ¦
    -0.59
    âĢ¦.
    -0.57
    âĢ¦."
    -0.56
    âĢ¦
    -0.53
     reckon
    -0.53
     Sutherland
    -0.52
    POSITIVE LOGITS
    /-
    0.90
    tenance
    0.81
    -+-+
    0.77
    fixed
    0.76
    =-
    0.76
    )-
    0.76
    !--
    0.76
    ãĤ´ãĥ³
    0.73
    recated
    0.71
    added
    0.70
    Activations Density 0.106%

    No Known Activations