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. 8-RES-JB
    6. 14800
    Prev
    Next
    INDEX
    Explanations

    phrases related to losing something or someone

    oai_token-act-pair · gpt-3.5-turbo

    references to loss and ownership of items or aspects of life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GGGGGGGG
    -0.81
    ocument
    -0.79
    edia
    -0.78
    Loading
    -0.73
    é¾
    -0.72
    Iss
    -0.70
    VEL
    -0.67
    aughtered
    -0.66
    ç«
    -0.66
    ihu
    -0.65
    POSITIVE LOGITS
     own
    1.23
     virginity
    1.14
     footing
    1.11
     sanity
    1.07
     rightful
    1.02
     bearings
    1.00
     grip
    0.97
     innocence
    0.97
     composure
    0.95
     individuality
    0.93
    Activations Density 0.111%

    No Known Activations