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. 3-RES-JB
    6. 18908
    Prev
    Next
    INDEX
    Explanations

    mentions of "I" or the first-person singular pronoun

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "I"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gutenberg
    -0.65
     Violet
    -0.65
     tides
    -0.60
     Butter
    -0.59
     adhesive
    -0.58
     electromagnetic
    -0.58
     decoration
    -0.57
    minster
    -0.57
     Conversion
    -0.57
     Replacement
    -0.57
    POSITIVE LOGITS
    'm
    1.33
    've
    1.07
     suppose
    1.04
    nex
    0.98
    MAX
    0.96
    ANA
    0.95
     am
    0.94
     guess
    0.94
    UC
    0.91
     presume
    0.90
    Activations Density 0.359%

    No Known Activations