© 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. 0-RES-JB
    11. 7667
    Prev
    Next
    INDEX
    Explanations

    words related to airships

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ship" and its variations

    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
     vulgar
    -0.70
     conservatives
    -0.66
     conservative
    -0.62
     Evans
    -0.61
     Kansas
    -0.59
     Ferguson
    -0.58
     Grac
    -0.57
     Collins
    -0.57
     Andrews
    -0.57
     defenders
    -0.57
    POSITIVE LOGITS
    ship
    4.86
    ships
    4.04
    SHIP
    2.13
    Ship
    2.13
    hips
    1.96
    hip
    1.66
     Ship
    1.50
     ship
    1.42
    boats
    1.31
    boat
    1.29
    Activations Density 0.014%

    No Known Activations