© 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. 4-RES-JB
    11. 10565
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by nouns or noun phrases

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "of course."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.66
    taboola
    -0.63
     reperto
    -0.62
     istg
    -0.62
     sew
    -0.61
    2200
    -0.60
    ocene
    -0.59
     cleaners
    -0.59
    pieces
    -0.58
    NetMessage
    -0.56
    POSITIVE LOGITS
     course
    1.24
    course
    0.90
    ortunately
    0.86
    onso
    0.86
    elia
    0.84
    sted
    0.83
     Course
    0.77
    rontal
    0.74
    ric
    0.72
     sorts
    0.72
    Activations Density 0.035%

    No Known Activations