© 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. 4-RES-JB
    11. 7300
    Prev
    Next
    INDEX
    Explanations

    phrases related to causing or inciting action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "prompt" and its variations, indicating triggers for actions or responses

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

    No Comments

    Negative Logits
    à©
    -0.64
     Nanto
    -0.63
     cannabinoid
    -0.62
    aird
    -0.62
     Cortex
    -0.61
     Leaves
    -0.61
    Sham
    -0.61
    avia
    -0.61
     Armen
    -0.60
    ihar
    -0.59
    POSITIVE LOGITS
     prompt
    1.17
     prompts
    1.06
     prompting
    0.93
     prompted
    0.86
    iration
    0.84
    ously
    0.81
     showc
    0.78
    rising
    0.77
    gers
    0.75
    FontSize
    0.74
    Activations Density 0.017%

    No Known Activations