© 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. 3468
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical events or significant figures

    oai_token-act-pair · gpt-3.5-turbo

    references to significant historical events and their origins

    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
    inventoryQuantity
    -0.86
    luck
    -0.79
    affected
    -0.76
     bidder
    -0.72
    treated
    -0.71
    hov
    -0.70
    uters
    -0.68
     regardless
    -0.67
    abuse
    -0.67
    TION
    -0.65
    POSITIVE LOGITS
     modern
    1.11
     infamous
    0.96
     famous
    0.89
     Modern
    0.87
     iconic
    0.84
     earliest
    0.82
     notion
    0.81
     famed
    0.80
     idea
    0.80
     seminal
    0.79
    Activations Density 0.299%

    No Known Activations