© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 12187
    Prev
    Next
    INDEX
    Explanations

    phrases related to planning or preparing for future events

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to planning and preparation for future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hari
    -0.78
    ©¶æ¥µ
    -0.71
    LER
    -0.69
     Advertisement
    -0.67
    milo
    -0.65
    Cola
    -0.64
    zai
    -0.64
     Originally
    -0.63
    mbuds
    -0.63
    ACTED
    -0.63
    POSITIVE LOGITS
     future
    1.79
     upcoming
    1.47
     foreseeable
    1.43
     eventual
    1.38
     next
    1.36
     impending
    1.33
     inevitable
    1.32
     forthcoming
    1.32
     possibility
    1.31
     hereafter
    1.28
    Activations Density 0.458%

    No Known Activations