Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 21755
    Prev
    Next
    INDEX
    Explanations

    words related to military bases

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific data structure or type in computing, particularly related to "base"

    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
     curtains
    -0.71
     Nev
    -0.69
     Gust
    -0.66
     lit
    -0.66
     answers
    -0.65
     limp
    -0.63
     Mous
    -0.59
     revel
    -0.59
     distress
    -0.58
    è¦
    -0.58
    POSITIVE LOGITS
    base
    4.33
    Base
    2.50
     base
    2.34
     Base
    2.13
     BASE
    1.80
     bases
    1.77
    frame
    1.11
    bas
    1.05
    abase
    1.04
    hub
    1.03
    Activations Density 0.007%

    No Known Activations