© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 22162
    Prev
    Next
    INDEX
    Explanations

    pairs of words that frequently appear together

    oai_token-act-pair · gpt-3.5-turbo

    a thematic or structural placeholder indicating the end of a document or section

    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
    GGGGGGGG
    -0.43
    Way
    -0.40
    Gall
    -0.40
    Got
    -0.38
    Gl
    -0.37
    standing
    -0.37
     Lon
    -0.36
    Merc
    -0.36
    Choice
    -0.36
    Sean
    -0.36
    POSITIVE LOGITS
     legalize
    0.74
     apologise
    0.71
     marry
    0.70
     organise
    0.70
     dissolve
    0.68
     liberate
    0.68
     merge
    0.68
     overwrite
    0.68
     migrate
    0.68
     reproduce
    0.67
    Activations Density 0.711%

    No Known Activations