© 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. 3-RES-JB
    11. 1933
    Prev
    Next
    INDEX
    Explanations

    related to commitment or loyalty

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sticking" and its variations, indicating a focus on adherence or commitment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NET
    -0.70
     Starship
    -0.69
     unfocusedRange
    -0.68
    eur
    -0.66
    OTO
    -0.65
    inators
    -0.65
    oding
    -0.65
    ãĥ´
    -0.62
    Technology
    -0.61
     è£ı
    -0.60
    POSITIVE LOGITS
     stick
    0.91
     plaster
    0.90
     sticks
    0.89
     sticking
    0.81
     blender
    0.75
    holders
    0.71
     Stick
    0.71
     toe
    0.70
    ciating
    0.69
    holder
    0.69
    Activations Density 0.009%

    No Known Activations