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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 17211
    Prev
    Next
    INDEX
    Explanations

    phrases related to royalty or prominent figures

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating authority or prominence, particularly related to titles or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    annis
    -0.68
    llah
    -0.67
    matic
    -0.64
    llor
    -0.62
    rouse
    -0.62
    eful
    -0.61
    urches
    -0.61
    Pope
    -0.61
     directly
    -0.60
    bishop
    -0.60
    POSITIVE LOGITS
     sorts
    0.86
     mankind
    0.82
     Gamergate
    0.73
     Mankind
    0.72
     nerds
    0.70
     humankind
    0.70
     hearts
    0.70
     modern
    0.68
     understatement
    0.67
     rap
    0.66
    Activations Density 0.156%

    No Known Activations