© 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. 11-RES-JB
    11. 22603
    Prev
    Next
    INDEX
    Explanations

    words related to individuals named "Brandon"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Brandon" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atics
    -0.72
    drivers
    -0.71
    atic
    -0.71
    atively
    -0.69
    arist
    -0.69
    ãĤ¦ãĤ¹
    -0.66
    cheat
    -0.64
    ystem
    -0.64
    heres
    -0.63
    opia
    -0.62
    POSITIVE LOGITS
     Wheat
    0.98
     Manning
    0.90
     Jennings
    0.88
     Ingram
    0.84
     Sands
    0.84
     Belt
    0.83
     Flowers
    0.83
     Stanton
    0.83
     Crawford
    0.82
     Morrow
    0.82
    Activations Density 0.039%

    No Known Activations