© 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. 0-RES-JB
    11. 22321
    Prev
    Next
    INDEX
    Explanations

    words related to names, especially the name "Heston."

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named "Heston."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Div
    -0.71
     Division
    -0.69
     cube
    -0.67
     cub
    -0.64
     Cub
    -0.64
     grade
    -0.64
     MK
    -0.64
     waves
    -0.62
     Rapt
    -0.62
     level
    -0.61
    POSITIVE LOGITS
    eston
    4.97
    estone
    1.51
    ottesville
    1.38
    otte
    1.19
    este
    1.13
    erville
    1.12
    estones
    1.11
    anchester
    1.09
    aston
    1.07
    erton
    1.07
    Activations Density 0.025%

    No Known Activations