© 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. 4-RES-JB
    11. 15191
    Prev
    Next
    INDEX
    Explanations

    the word "Prince" repeated throughout the text

    oai_token-act-pair · gpt-3.5-turbo

    references to royal figures, specifically "Prince."

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

    No Comments

    Negative Logits
    anwhile
    -0.79
    SOURCE
    -0.69
     fram
    -0.65
    bers
    -0.65
    CAST
    -0.65
    KT
    -0.65
    jriwal
    -0.63
    ulhu
    -0.63
    trak
    -0.62
    ĻĤ
    -0.62
    POSITIVE LOGITS
    loo
    0.93
    doms
    0.92
    cipled
    0.88
     Prince
    0.87
     Albert
    0.80
     Rupert
    0.80
    Prince
    0.78
     Clause
    0.76
    unciation
    0.72
     George
    0.71
    Activations Density 0.012%

    No Known Activations