© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13120
    Prev
    Next
    INDEX
    Explanations

    specific names of individuals, particularly Louis, with a high level of activation

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Louis."

    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
    BOOK
    -0.94
    ilk
    -0.64
    lished
    -0.63
     shr
    -0.63
    ×IJ
    -0.62
    OUT
    -0.62
     forth
    -0.62
    mit
    -0.61
    pled
    -0.61
    GAME
    -0.61
    POSITIVE LOGITS
     XIV
    1.07
     XVI
    1.05
    iana
    0.97
    bourg
    0.95
     CK
    0.95
     Vu
    0.92
     XIII
    0.89
     Louis
    0.85
     XV
    0.84
    inian
    0.83
    Activations Density 0.005%

    No Known Activations