© 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. 0-RES-JB
    11. 16455
    Prev
    Next
    INDEX
    Explanations

    phrases related to focusing or concentration

    oai_token-act-pair · gpt-3.5-turbo
    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
    hern
    -0.80
     orderly
    -0.73
     disorderly
    -0.70
     ther
    -0.70
    âĿ
    -0.69
     pir
    -0.68
    lyn
    -0.68
     topp
    -0.67
     inval
    -0.67
     impro
    -0.66
    POSITIVE LOGITS
     Focus
    3.93
    Focus
    3.48
    focus
    2.28
     focus
    1.72
    focused
    1.37
    ocus
    1.33
     Insight
    1.30
    ocused
    1.29
     focusing
    1.27
    ocusing
    1.23
    Activations Density 0.019%

    No Known Activations