© 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. 7-RES-JB
    11. 22847
    Prev
    Next
    INDEX
    Explanations

    the phrase "best way to" followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate methods or ways to achieve something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lights
    -0.77
    bags
    -0.70
     Klu
    -0.69
    pins
    -0.68
    mails
    -0.68
    pict
    -0.67
    naires
    -0.66
     Needs
    -0.66
    listed
    -0.65
    boxing
    -0.64
    POSITIVE LOGITS
     communicate
    1.26
     achieve
    1.24
     accomplish
    1.18
     maximize
    1.14
     resolve
    1.13
     navigate
    1.13
     circumvent
    1.12
     avoid
    1.11
     visualize
    1.11
     organize
    1.10
    Activations Density 0.075%

    No Known Activations