© 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 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. 22384
    Prev
    Next
    INDEX
    Explanations

    phrases related to the United States Soccer organization (USS)

    oai_token-act-pair · gpt-3.5-turbo

    the term "uss" used in various contexts

    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
    bably
    -0.70
    attled
    -0.67
    thing
    -0.67
    vation
    -0.66
    estine
    -0.63
    ©¶æ
    -0.61
    thens
    -0.61
    GY
    -0.60
    ISO
    -0.59
    ths
    -0.57
    POSITIVE LOGITS
    engers
    1.25
    olini
    1.13
    alam
    1.04
    enger
    1.00
    enegger
    0.98
    ures
    0.92
    kaya
    0.86
    alez
    0.86
    edIn
    0.86
    iness
    0.85
    Activations Density 0.037%

    No Known Activations