© 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. 1-RES-JB
    11. 3952
    Prev
    Next
    INDEX
    Explanations

    names of or related to public figures, especially focusing on the surname "Sasse"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "assess"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istically
    -0.64
    iggins
    -0.62
    ODUCT
    -0.62
    ests
    -0.61
    opsy
    -0.60
    owment
    -0.60
     glam
    -0.60
     opener
    -0.60
     exemplary
    -0.59
    od
    -0.59
    POSITIVE LOGITS
    asse
    1.36
    xual
    0.87
    uve
    0.81
    furt
    0.78
    bec
    0.78
    anu
    0.78
    rette
    0.76
    daq
    0.76
    rand
    0.74
     Hollande
    0.73
    Activations Density 0.008%

    No Known Activations