© 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 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. 1790
    Prev
    Next
    INDEX
    Explanations

    words related to fulfilling tasks or obligations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to fulfilling obligations or responsibilities

    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
    oxin
    -0.87
    oss
    -0.72
    perature
    -0.72
    otin
    -0.68
    weed
    -0.64
     fined
    -0.62
    iewicz
    -0.62
     separating
    -0.62
    brow
    -0.62
    opers
    -0.61
    POSITIVE LOGITS
     fulfil
    1.04
     fulf
    0.99
    ment
    0.97
     fulfilled
    0.96
     fulfillment
    0.93
     fulfill
    0.89
     prophecy
    0.88
     obligations
    0.87
    ments
    0.84
     expectations
    0.79
    Activations Density 0.040%

    No Known Activations