Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 7519
    Prev
    Next
    INDEX
    Explanations

    phrases related to locations near the Atlantic Ocean

    oai_token-act-pair · gpt-3.5-turbo

    references to the Atlantic Ocean and related geographical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    perse
    -0.84
    etsk
    -0.79
    giving
    -0.76
    PER
    -0.76
    baugh
    -0.74
    FUL
    -0.74
    INGTON
    -0.74
    BACK
    -0.71
    ithing
    -0.71
    criptions
    -0.69
    POSITIVE LOGITS
     Ocean
    1.17
     Highlands
    1.01
     Atlantic
    1.00
     Yards
    0.95
     Coast
    0.93
     Wire
    0.89
     Warfare
    0.82
     Sunrise
    0.81
    ampion
    0.81
     Shore
    0.81
    Activations Density 0.012%

    No Known Activations