© 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. 1-RES-JB
    11. 24129
    Prev
    Next
    INDEX
    Explanations

    phrases or names related to a person named Nicholas

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Nicholas."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebook
    -0.85
    java
    -0.77
    regn
    -0.73
    employment
    -0.73
    marked
    -0.72
    views
    -0.71
    verb
    -0.70
    Indian
    -0.70
    loaded
    -0.68
    joined
    -0.67
    POSITIVE LOGITS
    olas
    1.24
     Nicholas
    1.22
     Cage
    0.99
    Nich
    0.87
    ettings
    0.85
     traged
    0.80
    uity
    0.79
    olson
    0.77
    heon
    0.75
     Nicolas
    0.75
    Activations Density 0.004%

    No Known Activations