© 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. 3315
    Prev
    Next
    INDEX
    Explanations

    references to titles or names that contain the word "Lord"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Lord."

    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
    ¥ŀ
    -0.89
    ascus
    -0.75
    usp
    -0.70
    Marginal
    -0.70
    misc
    -0.66
    urses
    -0.66
    single
    -0.65
    ickr
    -0.65
    NAT
    -0.64
     conduc
    -0.64
    POSITIVE LOGITS
    Lord
    1.13
    lord
    1.06
     Lord
    0.97
    ess
    0.90
    stown
    0.89
     Vader
    0.89
    buster
    0.88
    friend
    0.87
    lords
    0.87
     Almighty
    0.83
    Activations Density 0.007%

    No Known Activations