© 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. 8-RES-JB
    11. 4306
    Prev
    Next
    INDEX
    Explanations

    references to names or terms related to specific entities or places

    oai_token-act-pair · gpt-3.5-turbo

    words related to "Tar" and associated topics or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĨĴ
    -0.78
    theless
    -0.77
    earch
    -0.67
    shire
    -0.65
    lihood
    -0.65
    es
    -0.65
     Zimmer
    -0.62
    erver
    -0.62
    ¬¼
    -0.61
    vous
    -0.60
    POSITIVE LOGITS
     sands
    1.09
    iffs
    1.08
    zan
    0.97
    ãĥ£
    0.88
    thur
    0.87
    riors
    0.87
    onga
    0.86
    geon
    0.86
    iff
    0.85
    oux
    0.85
    Activations Density 0.030%

    No Known Activations