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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 5503
    Prev
    Next
    INDEX
    Explanations

    phrases related to concentration or prioritization

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the word "focus."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idden
    -0.70
    named
    -0.67
    added
    -0.65
    mia
    -0.63
    ania
    -0.62
    eries
    -0.61
     Gleaming
    -0.61
    ston
    -0.61
     attest
    -0.61
    OUGH
    -0.60
    POSITIVE LOGITS
    rite
    0.90
     focus
    0.86
    Focus
    0.83
    peed
    0.81
    starter
    0.80
    rals
    0.80
    focus
    0.79
     attention
    0.77
     Focus
    0.77
     focusing
    0.77
    Activations Density 0.024%

    No Known Activations