© 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. 3382
    Prev
    Next
    INDEX
    Explanations

    words related to gradual change or progression

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "gradually" indicating ongoing change or transition over time

    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
     IMAGES
    -0.87
     Fancy
    -0.73
    YES
    -0.70
    lua
    -0.68
     Americas
    -0.68
    ORE
    -0.67
    EO
    -0.66
    don
    -0.64
     Mouth
    -0.63
    Performance
    -0.62
    POSITIVE LOGITS
     gradually
    1.30
     progressively
    1.13
     phased
    1.09
     gradual
    1.05
     "$:/
    0.99
     progressing
    0.93
     transitioning
    0.90
     steadily
    0.88
     destro
    0.86
     phases
    0.86
    Activations Density 0.015%

    No Known Activations