© 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. 2-RES-JB
    11. 3915
    Prev
    Next
    INDEX
    Explanations

    mentions of things that are officially registered

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "registered."

    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
    wich
    -0.83
    ï¸ı
    -0.77
     Galile
    -0.75
     Situation
    -0.74
    lihood
    -0.71
    ilitarian
    -0.65
    Ľ
    -0.65
    chie
    -0.64
    sis
    -0.63
     Mandela
    -0.63
    POSITIVE LOGITS
     trademarks
    0.99
     registered
    0.84
     registration
    0.81
    emark
    0.80
    registered
    0.78
     tradem
    0.75
     registering
    0.75
     trademark
    0.74
     register
    0.74
    ifying
    0.74
    Activations Density 0.012%

    No Known Activations