© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 10668
    Prev
    Next
    INDEX
    Explanations

    phrases related to pricing and costs

    oai_token-act-pair · gpt-3.5-turbo

    pricing information and promotional offers

    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
    æ³
    -0.70
    hew
    -0.69
    angelo
    -0.68
    stakes
    -0.68
    soDeliveryDate
    -0.67
    hess
    -0.67
    ghazi
    -0.65
    too
    -0.63
    arget
    -0.63
    Gamer
    -0.62
    POSITIVE LOGITS
     each
    1.09
     starters
    0.97
     every
    0.90
     singles
    0.86
    geries
    0.84
    each
    0.83
    ints
    0.81
     adults
    0.78
     instance
    0.78
     beginners
    0.77
    Activations Density 0.100%

    No Known Activations