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. 3-RES-JB
    6. 11623
    Prev
    Next
    INDEX
    Explanations

    mentions or instances of the term "cadet"

    oai_token-act-pair · gpt-3.5-turbo

    the term "cadet" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Borders
    -0.79
     Mutual
    -0.67
     pity
    -0.66
     luck
    -0.61
    IELD
    -0.61
    à
    -0.61
     Kubrick
    -0.60
    square
    -0.60
    Ther
    -0.60
     Werewolf
    -0.59
    POSITIVE LOGITS
     cad
    1.14
    illac
    0.98
    estones
    0.96
     Cad
    0.87
    alions
    0.85
    ulla
    0.83
    alog
    0.82
    adena
    0.80
    eter
    0.80
     princ
    0.80
    Activations Density 0.007%

    No Known Activations