© 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. 8-RES-JB
    11. 9840
    Prev
    Next
    INDEX
    Explanations

    references to cruise-related activities or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "cruise."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    older
    -0.76
    ĪĴ
    -0.75
    endi
    -0.75
    rity
    -0.74
    iates
    -0.72
    arov
    -0.71
    lr
    -0.69
    iate
    -0.69
    iotic
    -0.69
    ij士
    -0.69
    POSITIVE LOGITS
     cruise
    1.12
     Cruise
    1.05
    boat
    1.03
     sailing
    1.02
    boats
    1.00
     ship
    0.96
     sailed
    0.95
     sail
    0.95
    fleet
    0.91
     ferry
    0.91
    Activations Density 0.039%

    No Known Activations