© 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. 11387
    Prev
    Next
    INDEX
    Explanations

    specific characters that might indicate a break in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical values associated with events or statistics

    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
     endeav
    -0.71
    ardless
    -0.70
     endeavour
    -0.70
     appe
    -0.67
     regenerate
    -0.65
    utic
    -0.65
     incarn
    -0.63
     attent
    -0.63
    kees
    -0.63
    ĸļ
    -0.63
    POSITIVE LOGITS
    ccording
    1.09
    SPONSORED
    1.07
    Meanwhile
    1.06
    Advertisement
    0.98
    Neither
    0.95
    Newsletter
    0.95
    However
    0.93
    Bloomberg
    0.93
    Despite
    0.92
    Still
    0.88
    Activations Density 1.594%

    No Known Activations