© 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. 7-RES-JB
    11. 16761
    Prev
    Next
    INDEX
    Explanations

    phrases related to the name "Jake"

    oai_token-act-pair · gpt-3.5-turbo

    words that include the substring "ake."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ancial
    -0.70
    inatory
    -0.70
    ãĥ£
    -0.69
    ãĤ¡
    -0.67
    aldi
    -0.63
    enegger
    -0.63
    swick
    -0.63
    oad
    -0.61
     Weasley
    -0.61
    cfg
    -0.60
    POSITIVE LOGITS
    warm
    0.81
    hower
    0.78
    holder
    0.75
    yi
    0.74
    akes
    0.72
    maker
    0.72
    asy
    0.72
    velop
    0.71
    aimon
    0.71
    yers
    0.71
    Activations Density 0.033%

    No Known Activations