Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 23426
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific university (Tufts University) in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Tu" or related phrases

    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
    Ö¼
    -0.80
    manship
    -0.76
    å°Ĩ
    -0.76
    rawdownloadcloneembedreportprint
    -0.74
    éĹĺ
    -0.74
    âķIJ
    -0.74
    ãĤ®
    -0.73
    âĸ¬
    -0.73
     Rebirth
    -0.73
    é¾į
    -0.67
    POSITIVE LOGITS
    fts
    1.08
    Tu
    1.04
    ples
    1.02
    esta
    0.97
    culosis
    0.96
    pper
    0.89
     Klux
    0.87
    itton
    0.85
    isine
    0.85
    pping
    0.84
    Activations Density 0.007%

    No Known Activations