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. 241
    Prev
    Next
    INDEX
    Explanations

    parts of text that are separated by parentheses

    oai_token-act-pair · gpt-3.5-turbo

    parentheses

    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
     appropri
    -0.79
     veget
    -0.77
     invari
    -0.71
     planting
    -0.67
     erect
    -0.66
     charge
    -0.66
     gems
    -0.66
     appreci
    -0.65
     impe
    -0.65
     inund
    -0.65
    POSITIVE LOGITS
    *)
    1.36
    Courtesy
    1.13
    MORE
    1.08
    Vis
    1.07
    Note
    1.06
    Updated
    1.04
    Reuters
    1.03
    Editor
    1.02
    CNN
    1.02
    BOOK
    1.01
    Activations Density 0.021%

    No Known Activations