© 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. 2-RES-JB
    11. 23685
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically the name "Frederick."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Frederick" and its variations

    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
    hazard
    -0.76
    appropriate
    -0.75
    spir
    -0.75
    growth
    -0.71
    ilk
    -0.71
    aho
    -0.71
    kept
    -0.69
    Action
    -0.69
    Widget
    -0.69
    Brain
    -0.67
    POSITIVE LOGITS
    erick
    1.10
     Frederick
    1.07
    士
    0.94
    dinand
    0.89
     Engels
    0.87
     Dou
    0.86
    uania
    0.82
    shire
    0.80
    sson
    0.79
    nesday
    0.76
    Activations Density 0.010%

    No Known Activations