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. 4-RES-JB
    6. 3030
    Prev
    Next
    INDEX
    Explanations

    proper nouns starting with the letter "J"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the letter "J" or proper names that start with "J."

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

    No Comments

    Negative Logits
    holders
    -0.91
    holder
    -0.69
    TPPStreamerBot
    -0.68
    dayName
    -0.67
     Growing
    -0.63
     DeVos
    -0.63
     Soviets
    -0.63
     captcha
    -0.62
     Anthem
    -0.62
     diapers
    -0.60
    POSITIVE LOGITS
    ealous
    1.21
    igsaw
    1.21
    itsu
    1.15
    umbo
    1.15
    upiter
    1.14
    ordan
    1.14
    ournals
    1.13
    okes
    1.10
    ourn
    1.09
    umper
    1.09
    Activations Density 0.035%

    No Known Activations