© 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. 4-RES-JB
    11. 16884
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to sports teams

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Blue" in team or organization names

    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
    Ö¼
    -0.96
     srfAttach
    -0.85
    enegger
    -0.79
    uador
    -0.76
    ROR
    -0.75
    PsyNetMessage
    -0.73
    ITED
    -0.72
    ̶
    -0.71
     IPM
    -0.71
    ILY
    -0.70
    POSITIVE LOGITS
    grass
    1.28
    berry
    1.13
    prints
    1.12
    bird
    1.02
     Ribbon
    0.98
    hawk
    0.93
    heart
    0.86
    erton
    0.86
     Angels
    0.85
    fin
    0.84
    Activations Density 0.013%

    No Known Activations