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. 9-RES-JB
    6. 22562
    Prev
    Next
    INDEX
    Explanations

    sets of numbers in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Muslims
    -0.74
    grass
    -0.69
    Contribut
    -0.66
    anthrop
    -0.65
    Upload
    -0.63
    Americans
    -0.63
    Publisher
    -0.62
    upload
    -0.61
    creat
    -0.61
    WARE
    -0.60
    POSITIVE LOGITS
     etc
    1.31
    etc
    1.00
    ...)
    0.91
     ...
    0.79
    â̦)
    0.77
     respectively
    0.74
     â̦
    0.72
     &
    0.69
     ..
    0.67
    andr
    0.67
    Activations Density 0.108%

    No Known Activations