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. 8-RES-JB
    6. 3607
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and verbs referring to actions, particularly in a narrative context

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and their associated relationships or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĨĴ
    -0.72
    ãĤ´ãĥ³
    -0.71
     Saunders
    -0.68
     Attention
    -0.67
     Transactions
    -0.65
     Marlins
    -0.63
    Ĥ¬
    -0.63
    Skip
    -0.63
     Twice
    -0.63
    yip
    -0.62
    POSITIVE LOGITS
    'll
    0.99
     consequently
    0.96
    're
    0.90
     proceeded
    0.87
     secondly
    0.86
    rises
    0.83
    athered
    0.82
    athing
    0.81
     accordingly
    0.80
    aving
    0.79
    Activations Density 0.247%

    No Known Activations