© 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. 0-RES-JB
    11. 11296
    Prev
    Next
    INDEX
    Explanations

    words related to money, payment, or pricing

    oai_token-act-pair · gpt-3.5-turbo

    words related to pricing and costs, particularly in the context of transportation options

    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
    insky
    -0.68
    ousands
    -0.66
    atom
    -0.63
     Woods
    -0.62
    rosis
    -0.60
     Creat
    -0.60
     Painter
    -0.59
    oval
    -0.58
    head
    -0.58
    Untitled
    -0.57
    POSITIVE LOGITS
     fare
    4.42
     fares
    3.02
     fared
    1.73
     Fare
    1.65
    fare
    1.41
     ticket
    1.10
     ride
    1.08
     rides
    1.07
     passengers
    0.92
     Ticket
    0.89
    Activations Density 0.018%

    No Known Activations