© 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. 11-RES-JB
    11. 4814
    Prev
    Next
    INDEX
    Explanations

    phrases related to missions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "mission" alongside related numerical and contextual references

    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
     Ange
    -0.75
    tymology
    -0.68
    ãģį
    -0.66
    Column
    -0.66
    bart
    -0.64
    olor
    -0.64
     Oo
    -0.62
    jen
    -0.62
    au
    -0.62
    Mini
    -0.62
    POSITIVE LOGITS
     accomplished
    1.04
     statement
    0.99
     Impossible
    0.91
     accomplishment
    0.88
     undertaken
    0.87
     Statement
    0.85
     Directorate
    0.82
     Vie
    0.82
     creep
    0.81
    ary
    0.78
    Activations Density 0.027%

    No Known Activations