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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 23123
    Prev
    Next
    INDEX
    Explanations

    words related to a specific name "Hubert"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Bert."

    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
    heed
    -0.82
    esthetic
    -0.80
    creen
    -0.75
    ntil
    -0.67
    IFT
    -0.66
    igation
    -0.66
    ptive
    -0.66
    kar
    -0.65
    phan
    -0.65
    istant
    -0.64
    POSITIVE LOGITS
    atoes
    0.88
    aneous
    0.79
     Hoover
    0.76
    anza
    0.75
    ãĤ¡
    0.75
    IBLE
    0.71
    anan
    0.69
    itles
    0.68
     Hamb
    0.68
    rade
    0.67
    Activations Density 0.031%

    No Known Activations