© 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. 1-RES-JB
    11. 3707
    Prev
    Next
    INDEX
    Explanations

    words related to ease or ease of use

    oai_token-act-pair · gpt-3.5-turbo

    terms related to simplicity or convenience in processes or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nesium
    -0.68
    liam
    -0.68
     Prometheus
    -0.65
    oons
    -0.64
     Canary
    -0.64
    clusions
    -0.64
    ortium
    -0.64
    nant
    -0.64
    iverse
    -0.62
    Companies
    -0.62
    POSITIVE LOGITS
     ease
    1.22
     easing
    0.95
    terness
    0.85
     relief
    0.83
     eased
    0.80
    ilitation
    0.80
    ï¸
    0.78
     "$:/
    0.78
    liness
    0.76
     acquaint
    0.75
    Activations Density 0.009%

    No Known Activations