© 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. 13722
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a call to action or prompting the reader to take a specific step

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Enter."

    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
     Archangel
    -0.69
     relayed
    -0.63
     backdrop
    -0.63
    packs
    -0.63
     conviction
    -0.62
     laundering
    -0.60
     served
    -0.58
    packing
    -0.58
     orient
    -0.57
     grounded
    -0.57
    POSITIVE LOGITS
    prise
    1.81
    prises
    1.71
    tainment
    1.69
    prising
    1.51
    taining
    1.44
    tain
    1.36
    prisingly
    0.94
    TAIN
    0.91
    tained
    0.91
    igible
    0.80
    Activations Density 0.018%

    No Known Activations