© 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. 17347
    Prev
    Next
    INDEX
    Explanations

    keywords related to giving advice or suggestions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that offer advice or recommendations

    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
    ufact
    -0.75
    eals
    -0.69
    ords
    -0.68
    ruciating
    -0.67
     Palest
    -0.65
     Cav
    -0.65
    lihood
    -0.65
    minist
    -0.64
    ipment
    -0.63
    yss
    -0.61
    POSITIVE LOGITS
     tips
    1.24
     tip
    1.09
    tip
    1.07
    Tip
    1.05
    tips
    1.02
    Tips
    1.01
     Tips
    0.92
    heet
    0.92
     tipping
    0.86
     Tip
    0.77
    Activations Density 0.013%

    No Known Activations