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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 879
    Prev
    Next
    INDEX
    Explanations

    content related to battles and fleets in a science fiction setting

    oai_token-act-pair · gpt-3.5-turbo

    terms related to space battles and military engagements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aukee
    -0.89
    Wisconsin
    -0.88
     Suzuki
    -0.80
    Chicago
    -0.80
    erella
    -0.78
    nyder
    -0.76
    parents
    -0.75
    olkien
    -0.75
     Babe
    -0.74
    agogue
    -0.74
    POSITIVE LOGITS
     starship
    1.53
     Imperium
    1.44
     Starfleet
    1.42
     Planetary
    1.42
     Starship
    1.40
     Warp
    1.38
     Orbital
    1.36
     fleets
    1.34
     Federation
    1.33
     EVE
    1.31
    Activations Density 0.515%

    No Known Activations