© 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. 3234
    Prev
    Next
    INDEX
    Explanations

    instances where attention is being paid or drawn to specific subjects or details

    oai_token-act-pair · gpt-3.5-turbo

    references to attention and its significance

    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
    lins
    -0.67
     Tale
    -0.66
    nia
    -0.65
     Rebell
    -0.61
     Tycoon
    -0.61
    mos
    -0.61
     Mehran
    -0.60
     testament
    -0.60
     Vers
    -0.60
    ston
    -0.59
    POSITIVE LOGITS
     spans
    1.14
     span
    1.12
     attention
    0.92
     gaze
    0.82
    orial
    0.80
     scrutiny
    0.77
     grabbing
    0.77
    grab
    0.77
     Attention
    0.76
     seekers
    0.74
    Activations Density 0.035%

    No Known Activations