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

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 13045
    Prev
    Next
    INDEX
    Explanations

    words related to water or aquatic environments

    oai_token-act-pair · gpt-3.5-turbo

    references to aquatic life or environments

    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
     TS
    -0.84
     Frankfurt
    -0.77
     Koreans
    -0.72
     Whip
    -0.71
    pload
    -0.71
     Korea
    -0.70
     Victims
    -0.66
    urst
    -0.66
     Violence
    -0.66
     Bolton
    -0.66
    POSITIVE LOGITS
     aqu
    3.86
    aqu
    2.78
     Aqu
    2.15
     aquarium
    1.68
     aquatic
    1.65
     groundwater
    1.47
     Aqua
    1.36
     freshwater
    1.25
     amph
    1.24
    acqu
    1.14
    Activations Density 0.030%

    No Known Activations