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. 4-RES-JB
    6. 5691
    Prev
    Next
    INDEX
    Explanations

    phrases related to items or events being completely sold out

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating something being sold out

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

    No Comments

    Negative Logits
    lev
    -0.67
     clar
    -0.62
     Pillar
    -0.59
     Boxing
    -0.58
    tip
    -0.58
    Nav
    -0.58
    hest
    -0.57
    ogue
    -0.57
    rador
    -0.57
    CTV
    -0.57
    POSITIVE LOGITS
    wagen
    0.85
    abase
    0.81
     TAMADRA
    0.80
    hyde
    0.78
    ulz
    0.78
     kcal
    0.74
    undown
    0.70
    ettes
    0.70
    irts
    0.69
    ancies
    0.68
    Activations Density 0.026%

    No Known Activations