© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 18429
    Prev
    Next
    INDEX
    Explanations

    mentions of the color turquoise

    oai_token-act-pair · gpt-3.5-turbo

    references to the color turquoise

    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
     [&
    -0.77
    soDeliveryDate
    -0.66
     newsletters
    -0.64
    URES
    -0.64
    ERC
    -0.62
     Titanic
    -0.62
     Known
    -0.60
     largeDownload
    -0.60
    é¾įå
    -0.59
    urance
    -0.59
    POSITIVE LOGITS
    moil
    1.24
    kish
    1.16
    geon
    1.14
    fing
    1.12
    bul
    1.11
    ban
    1.06
    pees
    1.05
    lette
    1.05
    vy
    1.05
    iosity
    1.03
    Activations Density 0.026%

    No Known Activations