© 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. 2-RES-JB
    11. 7770
    Prev
    Next
    INDEX
    Explanations

    dates or references to specific historical events

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years in historical contexts

    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
    amin
    -0.78
    ularity
    -0.77
    iant
    -0.77
    imon
    -0.75
    ortium
    -0.74
    umen
    -0.71
    ective
    -0.70
    lig
    -0.69
    unders
    -0.69
    isman
    -0.68
    POSITIVE LOGITS
     1916
    1.07
     1914
    0.92
     1918
    0.92
     1915
    0.91
     1909
    0.89
     1917
    0.89
    ĸļ
    0.83
     1908
    0.81
    terness
    0.81
     1919
    0.81
    Activations Density 0.016%

    No Known Activations