© 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 EvalsExportsAPI 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. 10-RES-JB
    11. 5746
    Prev
    Next
    INDEX
    Explanations

    phrases related to directing attention or efforts towards specific goals or topics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "focus" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iop
    -0.72
    çļ
    -0.64
    named
    -0.64
    corn
    -0.60
    BIT
    -0.60
    OUGH
    -0.60
    anne
    -0.58
    assian
    -0.58
    posted
    -0.57
     Gleaming
    -0.57
    POSITIVE LOGITS
     attention
    1.13
     solely
    0.97
     Attention
    0.94
     attent
    0.94
     squarely
    0.92
     on
    0.88
     primarily
    0.88
     focus
    0.88
    ussed
    0.86
     upon
    0.85
    Activations Density 0.044%

    No Known Activations