Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 7349
    Prev
    Next
    INDEX
    Explanations

    words related to focus or concentration

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "focusing."

    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
    wn
    -0.73
    edom
    -0.72
    lv
    -0.67
    fax
    -0.64
    areth
    -0.63
    Pg
    -0.61
    mx
    -0.59
    aled
    -0.59
     Merchant
    -0.59
     Cthulhu
    -0.58
    POSITIVE LOGITS
     focusing
    3.35
     concentrating
    2.42
     foc
    2.18
     focused
    2.08
     focus
    2.06
    ocusing
    1.96
     focuses
    1.89
     emphasizing
    1.79
    focus
    1.73
     highlighting
    1.56
    Activations Density 0.017%

    No Known Activations