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. 11-RES-JB
    6. 8459
    Prev
    Next
    INDEX
    Explanations

    personal pronouns

    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 @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gad
    -0.71
     Forth
    -0.69
     Pegasus
    -0.68
     Rhodes
    -0.64
     Chop
    -0.61
     Wellington
    -0.61
     JFK
    -0.60
    owship
    -0.58
     Jennings
    -0.58
     Highlands
    -0.58
    POSITIVE LOGITS
    âĢ
    1.89
     âĢ
    1.36
    ï¸ı
    1.34
    Ò
    1.27
    â
    1.24
    âĢł
    1.22
    âĶ
    1.19
    ãĢ
    1.19
    Í
    1.19
    »
    1.18
    Activations Density 0.178%

    No Known Activations