© 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. 4-RES-JB
    11. 23731
    Prev
    Next
    INDEX
    Explanations

    words related to sports, particularly soccer

    oai_token-act-pair · gpt-3.5-turbo

    action-oriented verbs and terms related to sports gameplay events

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

    No Comments

    Negative Logits
    xon
    -0.97
     Alaska
    -0.89
     statewide
    -0.84
    Utah
    -0.84
    Larry
    -0.83
    GOP
    -0.82
    NJ
    -0.82
     Hawai
    -0.81
     Lyft
    -0.81
     Neighbor
    -0.80
    POSITIVE LOGITS
     footballer
    1.24
     defences
    1.17
     organisation
    1.14
     analyse
    1.14
     enqu
    1.11
     ageing
    1.10
     criticised
    1.10
     defence
    1.09
     centre
    1.06
     scept
    1.05
    Activations Density 0.235%

    No Known Activations