© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 386
    Prev
    Next
    INDEX
    Explanations

    numerical values and margins

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate winning or margin of victory in competitive contexts

    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
    abi
    -0.70
    ubric
    -0.64
    agate
    -0.64
    ashtra
    -0.62
     tatt
    -0.62
    aphael
    -0.62
    argon
    -0.62
    azine
    -0.59
    imen
    -0.58
     commenced
    -0.57
    POSITIVE LOGITS
     margin
    1.38
     margins
    1.20
     factor
    1.05
     percentage
    0.95
     ratio
    0.93
     landslide
    0.91
     mile
    0.75
     multiplier
    0.74
     Ratio
    0.73
    %.
    0.72
    Activations Density 0.086%

    No Known Activations