© 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. 2-RES-JB
    11. 17316
    Prev
    Next
    INDEX
    Explanations

    the word 'proceed'

    oai_token-act-pair · gpt-3.5-turbo

    the word "proceed" and its variations, indicating a focus on actions related to moving forward or continuing with tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    licks
    -0.69
    tal
    -0.67
    spl
    -0.65
    syn
    -0.65
    tem
    -0.65
    lder
    -0.64
    etimes
    -0.64
    aez
    -0.64
    tu
    -0.63
    stood
    -0.62
    POSITIVE LOGITS
     Proceed
    1.10
     proceeds
    0.98
     proceed
    0.98
     proceeded
    0.83
     "$:/
    0.83
    SourceFile
    0.79
    daq
    0.79
    ivism
    0.75
     onward
    0.75
    bilt
    0.75
    Activations Density 0.011%

    No Known Activations