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. 11795
    Prev
    Next
    INDEX
    Explanations

    actions related to user interaction, such as canceling, playing, saving, closing, adding comments, submitting ratings, sending emails, and becoming a supporter

    oai_token-act-pair · gpt-3.5-turbo

    commands or actions related to video and interaction options

    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
    ISC
    -0.67
    doms
    -0.65
    annis
    -0.64
    cale
    -0.64
    DragonMagazine
    -0.62
    hift
    -0.61
    clinton
    -0.60
    cream
    -0.60
    lav
    -0.60
    cultural
    -0.60
    POSITIVE LOGITS
     Cancel
    1.04
     Cue
    0.76
     Que
    0.70
     Button
    0.69
     Delete
    0.69
     Bulk
    0.67
     URL
    0.66
     Email
    0.66
     Oops
    0.65
     Skip
    0.65
    Activations Density 0.030%

    No Known Activations