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. 9-RES-JB
    6. 20429
    Prev
    Next
    INDEX
    Explanations

    verbs related to suggesting or recommending actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "propose" and its variations

    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
    ï¸ı
    -0.80
    brance
    -0.74
    isol
    -0.74
    oise
    -0.73
    uded
    -0.73
    verified
    -0.72
    mania
    -0.71
    set
    -0.71
    osterone
    -0.70
    stood
    -0.69
    POSITIVE LOGITS
     abandoning
    0.93
     alternatives
    0.91
     amendments
    0.91
     eliminating
    0.89
     arming
    0.89
     lowering
    0.87
     removing
    0.86
     modifying
    0.86
     withdrawing
    0.83
     replacing
    0.83
    Activations Density 0.105%

    No Known Activations