© 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. 2-RES-JB
    11. 19646
    Prev
    Next
    INDEX
    Explanations

    terms related to events or actions related to significant incidents, such as protests, performances, or tests

    oai_token-act-pair · gpt-3.5-turbo

    references to events, tests, and celebrations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģį
    -0.69
    missing
    -0.68
    awed
    -0.66
    ãģĦ
    -0.65
     pockets
    -0.63
    rising
    -0.61
    hidden
    -0.60
     corners
    -0.60
    ho
    -0.60
    relative
    -0.60
    POSITIVE LOGITS
    eers
    0.92
    enegger
    0.86
    naire
    0.84
    igraph
    0.83
    imony
    0.78
     spree
    0.76
    athon
    0.74
     laun
    0.73
    eering
    0.71
    eer
    0.70
    Activations Density 0.397%

    No Known Activations