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. 2-RES-JB
    6. 20363
    Prev
    Next
    INDEX
    Explanations

    car related terms, especially specific car models

    oai_token-act-pair · gpt-3.5-turbo

    specific terms and phrases related to cars and firearms, particularly focusing on brand names and technical aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -1.02
    osuke
    -0.77
    EGIN
    -0.76
     guiActiveUn
    -0.76
    rawdownloadcloneembedreportprint
    -0.75
    ————
    -0.74
    displayText
    -0.74
    ĨĴ
    -0.72
    VERTISEMENT
    -0.71
    buquerque
    -0.70
    POSITIVE LOGITS
     blades
    0.80
     liner
    0.79
    ocular
    0.75
     oven
    0.75
     basket
    0.74
     baskets
    0.73
    iron
    0.72
     tubes
    0.72
    ilts
    0.71
    jet
    0.69
    Activations Density 0.994%

    No Known Activations