© 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. 17687
    Prev
    Next
    INDEX
    Explanations

    phrases related to ships and ship-related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to ships and maritime 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
    âĶģ
    -0.80
    çīĪ
    -0.62
     plurality
    -0.61
     Fren
    -0.60
     Quan
    -0.60
     Chou
    -0.58
     Nuggets
    -0.58
    fusc
    -0.58
     Rasm
    -0.57
    hesis
    -0.57
    POSITIVE LOGITS
    wreck
    1.82
    yard
    1.46
    yards
    1.40
    wright
    1.28
     sailed
    1.23
     sailing
    1.20
    boat
    1.20
    building
    1.17
    boats
    1.16
    builder
    1.11
    Activations Density 0.090%

    No Known Activations