© 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. 0-RES-JB
    11. 18345
    Prev
    Next
    INDEX
    Explanations

    phrases related to history or historical events

    oai_token-act-pair · gpt-3.5-turbo

    references to historical context and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ainer
    -0.80
    rier
    -0.73
    zzle
    -0.73
    itter
    -0.73
     Lash
    -0.70
     lashes
    -0.69
    quit
    -0.68
    ploy
    -0.68
    Switch
    -0.67
    reens
    -0.67
    POSITIVE LOGITS
     historical
    3.31
     Historical
    2.48
     historic
    2.19
    hist
    2.00
    historic
    1.73
     histor
    1.72
     archaeological
    1.71
     historians
    1.71
     historically
    1.69
     history
    1.68
    Activations Density 0.016%

    No Known Activations