© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 17307
    Prev
    Next
    INDEX
    Explanations

    mentions of underwater environments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to underwater environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ========
    -0.93
    aign
    -0.91
    ============
    -0.90
    ====
    -0.85
    xx
    -0.85
    MQ
    -0.83
    Brand
    -0.81
    ================
    -0.81
    present
    -0.80
    cho
    -0.79
    POSITIVE LOGITS
     underwater
    1.29
     submerged
    1.03
     diving
    0.99
     mathemat
    0.92
     aquarium
    0.88
     landsl
    0.87
     submer
    0.85
    melon
    0.85
    ¥ŀ
    0.84
     aquatic
    0.82
    Activations Density 0.007%

    No Known Activations