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. 0-RES-JB
    6. 16245
    Prev
    Next
    INDEX
    Explanations

    image file formats like JPG and actions related to changing or downloading files

    oai_token-act-pair · gpt-3.5-turbo

    file extensions related to image and archive formats

    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
     dispens
    -0.83
     Consumer
    -0.75
    anian
    -0.74
     acquisition
    -0.69
     Agric
    -0.67
     practices
    -0.67
     safety
    -0.66
     Contra
    -0.66
     reception
    -0.66
     surrog
    -0.66
    POSITIVE LOGITS
    jpg
    3.96
    png
    2.95
    gif
    2.25
    pdf
    1.85
    txt
    1.82
    wav
    1.68
    htm
    1.63
    exe
    1.61
    zip
    1.58
    html
    1.54
    Activations Density 0.017%

    No Known Activations