© 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. 16298
    Prev
    Next
    INDEX
    Explanations

    phrases indicating imminent or near-future events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating impending actions or events

    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
    leck
    -0.81
    atively
    -0.74
    oret
    -0.65
    ocker
    -0.65
    htaking
    -0.65
    pel
    -0.65
    usage
    -0.65
    icion
    -0.65
    arth
    -0.64
    olding
    -0.64
    POSITIVE LOGITS
     thereafter
    0.97
    aneously
    0.90
     afterward
    0.81
     soon
    0.79
     afterwards
    0.77
    Soon
    0.73
    theless
    0.72
     Soon
    0.72
    mares
    0.72
     enough
    0.71
    Activations Density 0.015%

    No Known Activations