© 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. 5034
    Prev
    Next
    INDEX
    Explanations

    various rates of growth or change

    oai_token-act-pair · gpt-3.5-turbo

    data related to economic growth rates and trends

    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
     Presence
    -0.82
    ionics
    -0.69
    afia
    -0.65
     hangs
    -0.64
    eele
    -0.63
    HM
    -0.61
    laus
    -0.61
    wallet
    -0.60
    »Ĵ
    -0.60
    assis
    -0.60
    POSITIVE LOGITS
     rate
    1.45
     rates
    1.34
     pace
    1.25
     exponential
    1.19
     fastest
    1.15
     alarming
    1.12
     accelerating
    1.12
     accelerated
    1.11
     faster
    1.10
    rate
    1.07
    Activations Density 0.111%

    No Known Activations