© 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. 0-RES-JB
    11. 9445
    Prev
    Next
    INDEX
    Explanations

    words related to academic research such as "thesis" and "dissertation."

    oai_token-act-pair · gpt-3.5-turbo

    references to academic theses and dissertations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iform
    -0.70
    iba
    -0.62
     Enter
    -0.59
     Cookie
    -0.59
     signs
    -0.59
     populated
    -0.59
     CB
    -0.58
    whe
    -0.56
     unsafe
    -0.56
    acer
    -0.55
    POSITIVE LOGITS
     thesis
    3.95
     dissertation
    2.69
     hypothesis
    1.61
     theorem
    1.50
    ertation
    1.43
    sis
    1.39
     doctoral
    1.27
     hypotheses
    1.22
    ses
    1.19
     essay
    1.12
    Activations Density 0.010%

    No Known Activations