© 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. 644
    Prev
    Next
    INDEX
    Explanations

    phrases related to proper nouns, specifically those including the term "Tar"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Tar" and its various usages or contexts

    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
    theless
    -0.82
    shire
    -0.80
    lihood
    -0.79
    mble
    -0.72
    EY
    -0.69
    ¬¼
    -0.68
    ETF
    -0.67
    æĸ¹
    -0.67
    vous
    -0.66
    served
    -0.65
    POSITIVE LOGITS
    iffs
    1.01
    aji
    0.99
    zan
    0.93
     sands
    0.91
    onga
    0.88
    idon
    0.88
    iff
    0.86
    quel
    0.86
    thur
    0.85
    itans
    0.84
    Activations Density 0.007%

    No Known Activations