© 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. 16526
    Prev
    Next
    INDEX
    Explanations

    instances of words related to breaking, setting, or achieving records

    oai_token-act-pair · gpt-3.5-turbo

    terms related to record-breaking events or achievements

    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
     cart
    -0.72
    dot
    -0.67
    creen
    -0.64
    lez
    -0.64
    izabeth
    -0.62
    yg
    -0.62
    doms
    -0.62
    avascript
    -0.61
    otom
    -0.61
    utterstock
    -0.61
    POSITIVE LOGITS
     breaker
    1.15
    keeping
    1.11
     holder
    1.09
    breaking
    1.02
     highs
    0.86
    breaker
    0.85
     lows
    0.85
     Breaker
    0.85
     holders
    0.83
     Keeper
    0.83
    Activations Density 0.042%

    No Known Activations