© 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. 10-RES-JB
    11. 16686
    Prev
    Next
    INDEX
    Explanations

    words related to specific time periods or events

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to processes and timelines in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     artif
    -0.65
    lear
    -0.64
    MpServer
    -0.60
     Glover
    -0.60
     millenn
    -0.58
     annexed
    -0.58
    milo
    -0.56
     Slim
    -0.56
     artificial
    -0.55
     hacked
    -0.55
    POSITIVE LOGITS
     periods
    0.90
     period
    0.87
    uberty
    0.85
     onset
    0.85
    Footnote
    0.81
    enment
    0.80
    days
    0.80
     onwards
    0.78
    .
    0.76
     intervals
    0.76
    Activations Density 0.367%

    No Known Activations