© 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. 19252
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports and professional leagues

    oai_token-act-pair · gpt-3.5-turbo

    references to sports, particularly regarding professional and military service athletes

    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
     kW
    -0.67
     Plot
    -0.65
     Visual
    -0.62
     caption
    -0.61
     objects
    -0.60
    object
    -0.60
     object
    -0.59
     unity
    -0.58
     spherical
    -0.57
     Scal
    -0.57
    POSITIVE LOGITS
     stint
    1.11
     eligibility
    0.93
    ilitation
    0.89
     abroad
    0.89
     overseas
    0.88
    ilitating
    0.86
     minors
    0.84
     Career
    0.84
    querque
    0.83
    ploma
    0.81
    Activations Density 0.434%

    No Known Activations