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. 23262
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and verb phrases often used in conversational contexts

    oai_token-act-pair · gpt-3.5-turbo

    the use of personal pronouns, particularly "I" and "we."

    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
     Weston
    -0.80
     Polk
    -0.74
     Allied
    -0.65
     Clover
    -0.63
     Rapids
    -0.62
     Lake
    -0.62
     Salem
    -0.59
     Pearson
    -0.59
     Loren
    -0.59
     Florence
    -0.59
    POSITIVE LOGITS
    ãĢı
    0.90
    theless
    0.86
    `.
    0.84
    "—
    0.83
     dunno
    0.81
    zbollah
    0.80
    Í
    0.79
    [/
    0.78
    `
    0.78
    ãĢį
    0.77
    Activations Density 0.173%

    No Known Activations