Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 3265
    Prev
    Next
    INDEX
    Explanations

    references to electronic devices, particularly cell phones

    oai_token-act-pair · gpt-3.5-turbo

    references to mobile phones and other types of 'cells'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    manship
    -0.78
    Õ
    -0.76
     Stout
    -0.73
    deals
    -0.70
     Artemis
    -0.70
     Art
    -0.69
    issance
    -0.66
     Murray
    -0.66
     Apache
    -0.66
    kies
    -0.65
    POSITIVE LOGITS
     cell
    3.83
     Cell
    2.74
     cells
    2.72
    Cell
    2.56
    cell
    2.41
     Cells
    2.36
     cellular
    2.19
    cells
    1.92
     cellphone
    1.87
     Cellular
    1.67
    Activations Density 0.012%

    No Known Activations