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. 11-RES-JB
    6. 18429
    Prev
    Next
    INDEX
    Explanations

    mentions of Samsung Galaxy smartphone models

    oai_token-act-pair · gpt-3.5-turbo

    references to specific Samsung Galaxy smartphone models

    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
    ersen
    -0.88
     Carnegie
    -0.73
     Gutenberg
    -0.71
     Haitian
    -0.71
     hors
    -0.69
    Äĩ
    -0.67
    akespeare
    -0.66
     UNC
    -0.64
    displayText
    -0.64
     puppet
    -0.63
    POSITIVE LOGITS
    III
    0.93
     handset
    0.92
    6
    0.91
     smartphones
    0.91
    7
    0.91
    5
    0.88
    8
    0.88
     phones
    0.87
    650
    0.86
    ixels
    0.84
    Activations Density 0.038%

    No Known Activations