© 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. 8-RES-JB
    6. 1341
    Prev
    Next
    INDEX
    Explanations

    the phrase "of course."

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases indicating an exploration or commentary on various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reperto
    -0.72
     partName
    -0.70
    agher
    -0.65
    ovember
    -0.60
    YA
    -0.59
    grounds
    -0.58
    ptions
    -0.58
    pots
    -0.57
    pie
    -0.57
    7601
    -0.57
    POSITIVE LOGITS
     course
    1.99
    course
    1.69
     COUR
    1.36
     Course
    1.36
     sorts
    1.18
    Course
    1.07
    ortunately
    0.95
     courses
    0.94
     necessity
    0.83
    icial
    0.81
    Activations Density 0.098%

    No Known Activations