© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12724
    Prev
    Next
    INDEX
    Explanations

    phrases related to paving the way or preparing for something to happen

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating progress or groundwork being laid for future actions

    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
    ional
    -0.73
    TION
    -0.71
    whatever
    -0.71
    han
    -0.70
    hart
    -0.69
     depended
    -0.68
    ably
    -0.67
    keep
    -0.67
     outweigh
    -0.66
    leness
    -0.65
    POSITIVE LOGITS
     groundwork
    1.16
     path
    0.97
     foundations
    0.96
     pathway
    0.96
     basis
    0.95
     proverbial
    0.95
     gates
    0.94
     foundation
    0.93
     ground
    0.92
     fuse
    0.89
    Activations Density 0.094%

    No Known Activations