© 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. 10237
    Prev
    Next
    INDEX
    Explanations

    references to the Borussia Dortmund soccer team

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific football club

    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
     srfAttach
    -0.78
    uality
    -0.74
    IVER
    -0.71
    INESS
    -0.71
    IDER
    -0.67
    HER
    -0.67
    waves
    -0.67
    ULT
    -0.67
    ELL
    -0.66
    encers
    -0.65
    POSITIVE LOGITS
    ussia
    1.02
    mingham
    0.97
    chard
    0.95
    rome
    0.94
    ham
    0.94
    owitz
    0.92
    owski
    0.92
    bon
    0.85
    je
    0.84
    wana
    0.82
    Activations Density 0.043%

    No Known Activations