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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 6447
    Prev
    Next
    INDEX
    Explanations

    phrases related to the passage of time or progression

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of "course" in the context of duration or progression over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     assisted
    -0.71
    mented
    -0.68
    ilaterally
    -0.65
    rafted
    -0.65
    axter
    -0.62
     stake
    -0.61
    joice
    -0.61
    bi
    -0.61
    aples
    -0.60
    ictions
    -0.60
    POSITIVE LOGITS
    course
    1.09
     Course
    1.01
    Course
    1.00
     course
    0.99
     COUR
    0.95
    é¾įåĸļ士
    0.82
    \/\/
    0.68
    opian
    0.67
    ãĤ¡
    0.67
    ãĤ§
    0.67
    Activations Density 0.019%

    No Known Activations