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. 12952
    Prev
    Next
    INDEX
    Explanations

    statements starting with the pronoun "I."

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the first-person perspective in assertions or opinions

    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
    Reviewer
    -0.75
    ĸļ
    -0.71
    iquette
    -0.69
    rawdownloadcloneembedreportprint
    -0.68
     Reborn
    -0.65
     Hels
    -0.62
     Paste
    -0.62
     TMZ
    -0.61
     passers
    -0.61
     Abyss
    -0.60
    POSITIVE LOGITS
     think
    1.31
     believe
    1.08
     worry
    1.06
     disagree
    1.04
     agree
    1.00
     doubt
    0.99
     hope
    0.96
     frankly
    0.92
     suggest
    0.91
     reiterate
    0.91
    Activations Density 0.189%

    No Known Activations