© 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. 2-RES-JB
    11. 894
    Prev
    Next
    INDEX
    Explanations

    word roots related to practices and professions

    oai_token-act-pair · gpt-3.5-turbo

    the stem "pract" from words like "practice" or "practical"

    oai_token-act-pair · gpt-4-turbo

    terms related to practical application and practitioners in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rescue
    -0.75
    berry
    -0.66
     dwelling
    -0.65
     orphan
    -0.65
     peg
    -0.64
     Arab
    -0.62
     Libya
    -0.61
     kingdom
    -0.61
     Kickstarter
    -0.60
     hatch
    -0.60
    POSITIVE LOGITS
    icing
    1.26
    ices
    1.26
    icum
    1.16
    Pract
    1.16
    icial
    1.09
    icion
    1.07
    iced
    1.04
    isers
    1.01
     pract
    1.00
    isky
    1.00
    Activations Density 0.008%

    No Known Activations