© 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. 3-RES-JB
    11. 3229
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical conditions or terms with 'yt' or 'eret' in them

    oai_token-act-pair · gpt-3.5-turbo

    references to the New York Times and related abbreviations or terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    drawn
    -0.79
     congr
    -0.70
    testing
    -0.70
     Voting
    -0.68
    bable
    -0.66
    Cand
    -0.64
    interrupted
    -0.64
     recru
    -0.63
    ysis
    -0.61
     clerk
    -0.61
    POSITIVE LOGITS
    azo
    0.99
    olkien
    0.98
    olith
    0.94
    arget
    0.90
    ypes
    0.88
    te
    0.85
    uner
    0.84
    ür
    0.84
    oday
    0.84
    itles
    0.83
    Activations Density 0.015%

    No Known Activations