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

    Neuronpedia

    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. 11-RES-JB
    11. 1395
    Prev
    Next
    INDEX
    Explanations

    unexpected events or actions

    oai_token-act-pair · gpt-3.5-turbo

    words indicating significant events or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ̶
    -0.92
    ;;
    -0.81
    ;;;;
    -0.75
    ,,,,,,,,
    -0.74
    hovah
    -0.72
    obar
    -0.69
    olkien
    -0.69
    olean
    -0.69
    ||
    -0.68
    alian
    -0.68
    POSITIVE LOGITS
     arrangement
    1.24
     announcement
    1.23
     discrepancy
    1.13
     nature
    1.11
     approach
    1.08
     setback
    1.07
     findings
    1.06
     revelations
    1.05
     move
    1.04
     deadline
    1.03
    Activations Density 0.313%

    No Known Activations