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. 1-RES-JB
    6. 19793
    Prev
    Next
    INDEX
    Explanations

    verbs related to saving or preservation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "saved" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rush
    -0.72
    enberg
    -0.70
    LESS
    -0.69
    RY
    -0.68
    yond
    -0.68
    NE
    -0.65
    HOW
    -0.63
    Wr
    -0.61
     Continued
    -0.61
    ledge
    -0.60
    POSITIVE LOGITS
     saved
    0.98
     save
    0.92
    saving
    0.90
    apego
    0.90
    monton
    0.90
     Saving
    0.87
    Save
    0.87
     saves
    0.86
     saving
    0.85
     Save
    0.81
    Activations Density 0.007%

    No Known Activations