© 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. 8-RES-JB
    11. 3226
    Prev
    Next
    INDEX
    Explanations

    descriptions of soccer plays and game events

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sports events and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MFT
    -0.94
     FOIA
    -0.86
    CBS
    -0.83
    DAQ
    -0.80
     Canaver
    -0.79
     neighborhoods
    -0.79
    CNN
    -0.77
    FactoryReloaded
    -0.76
     honor
    -0.75
    NYSE
    -0.75
    POSITIVE LOGITS
     centre
    1.07
     goalkeeper
    1.05
     defences
    1.02
     manoeuv
    0.99
     defence
    0.98
     striker
    0.96
     stopp
    0.94
     scorer
    0.93
     clutch
    0.91
     metre
    0.90
    Activations Density 0.462%

    No Known Activations