© 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 EvalsExportsinterp-engineNEWAPI 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. 14316
    Prev
    Next
    INDEX
    Explanations

    sports-related events or competitions and outcomes

    oai_token-act-pair · gpt-3.5-turbo

    sports-related outcomes and events

    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
    ITNESS
    -0.64
    :{
    -0.63
    peak
    -0.59
    clus
    -0.59
    Translation
    -0.56
    EMENT
    -0.54
    anwhile
    -0.54
     agitation
    -0.53
    munition
    -0.52
    ctions
    -0.52
    POSITIVE LOGITS
     convinc
    1.15
     114
    1.06
     118
    1.06
     109
    1.04
     113
    1.04
     117
    1.04
     121
    1.03
     107
    1.03
     119
    1.02
     106
    1.02
    Activations Density 0.184%

    No Known Activations