© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1-RES-JB
    11. 20287
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical events or significant moments in history

    oai_token-act-pair · gpt-3.5-turbo

    references to significant historical events or figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.79
    eret
    -0.78
    gans
    -0.76
    flix
    -0.75
    ventus
    -0.74
    vous
    -0.73
    Various
    -0.73
    ringe
    -0.72
    utterstock
    -0.71
    Flow
    -0.70
    POSITIVE LOGITS
    orically
    1.06
     lows
    1.01
     landmark
    0.98
     historic
    0.93
     significance
    0.90
    orical
    0.83
     highs
    0.83
     preservation
    0.83
     landmarks
    0.81
     Revival
    0.75
    Activations Density 0.008%

    No Known Activations