© 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. 1344
    Prev
    Next
    INDEX
    Explanations

    words related to rules, laws, and regulations

    oai_token-act-pair · gpt-3.5-turbo

    topics related to gaming and legal issues

    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
    [/
    -0.67
     âĢ
    -0.66
     (%
    -0.66
    âĢ
    -0.64
    ãĢIJ
    -0.63
     âĢº
    -0.63
    /(
    -0.62
    /
    -0.61
     ·
    -0.61
     ®
    -0.61
    POSITIVE LOGITS
     elsewhere
    0.66
     already
    0.66
    yond
    0.60
     afterward
    0.58
     previously
    0.57
     else
    0.57
     later
    0.55
     everywhere
    0.55
     entire
    0.52
     previous
    0.51
    Activations Density 1.235%

    No Known Activations