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. 10-RES-JB
    6. 22660
    Prev
    Next
    INDEX
    Explanations

    actions or instructions indicating user interaction on digital platforms

    oai_token-act-pair · gpt-3.5-turbo

    actions related to interacting with buttons and user interfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    venge
    -0.72
    von
    -0.64
     choking
    -0.63
    762
    -0.60
    dyl
    -0.59
    iuses
    -0.59
    angering
    -0.58
    athlon
    -0.58
    ority
    -0.58
    dfx
    -0.57
    POSITIVE LOGITS
     Cancel
    1.13
     Apply
    1.04
     Save
    0.96
     Submit
    0.96
     Create
    0.93
     OK
    0.92
     Insert
    0.89
     Continue
    0.89
     Finish
    0.87
     Activate
    0.86
    Activations Density 0.048%

    No Known Activations