© 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. 18110
    Prev
    Next
    INDEX
    Explanations

    specific words related to ships

    oai_token-act-pair · gpt-3.5-turbo

    references to ships and boats

    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
     infrared
    -0.89
     ninja
    -0.83
     superpower
    -0.78
     ellipt
    -0.78
     locale
    -0.76
     MFT
    -0.74
     4096
    -0.73
     buffer
    -0.72
     analges
    -0.71
     latex
    -0.70
    POSITIVE LOGITS
     Ship
    2.75
     Boat
    2.44
    Ship
    1.80
     Step
    1.51
     Dock
    1.41
     Ships
    1.36
     Vessel
    1.32
     Lad
    1.31
     Roof
    1.28
     Tank
    1.27
    Activations Density 0.037%

    No Known Activations