© 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. 4-RES-JB
    11. 20843
    Prev
    Next
    INDEX
    Explanations

    the word "bots" at different levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    references to specific toys or themed objects, particularly ones that correlate to popular culture

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

    No Comments

    Negative Logits
     intimid
    -0.79
     acknow
    -0.70
     livest
    -0.69
     awa
    -0.69
     confir
    -0.68
     prosecut
    -0.67
     streng
    -0.66
    Reviewer
    -0.66
     Granger
    -0.65
     skelet
    -0.65
    POSITIVE LOGITS
    wana
    1.23
    anu
    1.08
    nikov
    1.04
    onga
    0.99
    heet
    0.98
    uba
    0.95
    assium
    0.94
    rons
    0.94
    weet
    0.91
    aku
    0.90
    Activations Density 0.012%

    No Known Activations