© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 19336
    Prev
    Next
    INDEX
    Explanations

    terms related to the act of practicing or carrying out actions consistently or systematically

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "practiced" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avour
    -0.71
     Dy
    -0.70
    £
    -0.68
    agraph
    -0.67
     Dunk
    -0.65
    Euro
    -0.65
     £
    -0.64
     Dimensions
    -0.62
    ode
    -0.60
    Closure
    -0.60
    POSITIVE LOGITS
     practiced
    3.52
     practicing
    3.30
     pract
    2.83
     practice
    2.54
     practise
    2.41
    practice
    2.28
     Practice
    2.25
    Pract
    2.19
    pract
    1.97
     practices
    1.79
    Activations Density 0.027%

    No Known Activations