Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 12354
    Prev
    Next
    INDEX
    Explanations

    references to royalty or titles associated with royalty

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various princes, particularly focusing on the name "Prince."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KT
    -0.66
    bers
    -0.65
     fram
    -0.64
    anwhile
    -0.63
    ãĤī
    -0.61
    £ı
    -0.61
     dispatch
    -0.60
    onica
    -0.59
    çĦ
    -0.59
    bered
    -0.59
    POSITIVE LOGITS
    loo
    0.97
    doms
    0.91
    cipled
    0.89
     Rupert
    0.84
     Prince
    0.78
     Clause
    0.77
     Albert
    0.76
    VPN
    0.75
    afort
    0.75
    pin
    0.74
    Activations Density 0.015%

    No Known Activations