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. 14712
    Prev
    Next
    INDEX
    Explanations

    phrases related to saving money, lives, or ideas

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "saving," whether it's saving resources, lives, or costs

    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
    liga
    -0.70
    naire
    -0.69
    ple
    -0.68
    æ©Ł
    -0.66
    interstitial
    -0.66
    akening
    -0.65
    rer
    -0.64
    secution
    -0.64
    oun
    -0.62
    hole
    -0.60
    POSITIVE LOGITS
     lives
    1.09
     Lives
    0.93
     face
    0.87
     souls
    0.84
     money
    0.81
    Instance
    0.81
     precious
    0.75
     countless
    0.73
    Save
    0.73
     valuable
    0.71
    Activations Density 0.040%

    No Known Activations