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. 10-RES-JB
    6. 19245
    Prev
    Next
    INDEX
    Explanations

    phrases related to bringing in or adding new elements or players to a team or group

    oai_token-act-pair · gpt-3.5-turbo

    phrases that discuss addition and improvement through bringing in new talent or competition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ®
    -0.84
    externalActionCode
    -0.83
    Flickr
    -0.79
    Enlarge
    -0.72
    CNN
    -0.71
    Consumer
    -0.71
    arta
    -0.71
    00000
    -0.70
    displayText
    -0.70
    Government
    -0.69
    POSITIVE LOGITS
     talented
    1.27
     rookies
    1.26
     inexperienced
    1.14
     newcomers
    1.08
     freshmen
    1.06
     plenty
    1.04
     veteran
    1.04
     starters
    1.03
     veterans
    1.02
     superstar
    1.00
    Activations Density 0.328%

    No Known Activations