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. 1567
    Prev
    Next
    INDEX
    Explanations

    phrases related to lawsuits and legal actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to success and 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
     Concern
    -0.65
    lev
    -0.65
     condemn
    -0.62
     stricken
    -0.60
    BuyableInstoreAndOnline
    -0.60
    cern
    -0.58
     blame
    -0.58
    Firstly
    -0.58
     Bearing
    -0.58
    given
    -0.57
    POSITIVE LOGITS
    Sounds
    1.08
     neat
    1.03
     seamless
    1.01
     simplicity
    0.98
     ingenious
    0.96
     clever
    0.92
     nifty
    0.91
     simplified
    0.90
     incentiv
    0.90
     achieves
    0.86
    Activations Density 0.531%

    No Known Activations