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

    Neuronpedia

    APICircuit 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. 10-RES-JB
    6. 23733
    Prev
    Next
    INDEX
    Explanations

    phrases with a conditional statement followed by a second person pronoun and a verb

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include conditional statements addressed to the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ñı
    -0.60
     Interface
    -0.58
    Summary
    -0.57
    ATER
    -0.56
    ãĥ¼ãĥĨ
    -0.56
    ifax
    -0.55
    burgh
    -0.55
     SOC
    -0.54
    BAT
    -0.53
     Pir
    -0.51
    POSITIVE LOGITS
     dare
    1.01
    ever
    0.89
     wanna
    0.88
     wills
    0.87
     ever
    0.85
     insist
    0.79
     dared
    0.78
     wish
    0.78
     survive
    0.77
    're
    0.76
    Activations Density 0.144%

    No Known Activations