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. 10538
    Prev
    Next
    INDEX
    Explanations

    keywords related to experienced or long-serving individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to veterans and their roles or statuses

    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
    atures
    -0.81
    olate
    -0.74
     Reply
    -0.72
     ãĤµ
    -0.69
     =>
    -0.69
    phones
    -0.67
     coerc
    -0.65
    ess
    -0.64
    wcsstore
    -0.64
    idae
    -0.63
    POSITIVE LOGITS
     veteran
    3.61
     veterans
    2.57
     Veteran
    2.48
    Veter
    2.05
     vets
    1.98
     vet
    1.76
     newcomer
    1.56
     Veterans
    1.53
     rookie
    1.50
     seasoned
    1.48
    Activations Density 0.011%

    No Known Activations