© 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. 9-RES-JB
    11. 9957
    Prev
    Next
    INDEX
    Explanations

    verbs related to fulfilling actions or obligations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to fulfilling responsibilities or commitments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oss
    -0.68
    Pol
    -0.67
    pt
    -0.64
    ahon
    -0.63
    iser
    -0.62
    weed
    -0.61
    etheless
    -0.60
    colo
    -0.60
    brow
    -0.60
    aster
    -0.59
    POSITIVE LOGITS
     obligations
    1.06
     expectations
    0.98
     prophecy
    0.93
     promises
    0.90
     contractual
    0.87
     prophe
    0.87
     requests
    0.85
     prophes
    0.85
     warranties
    0.84
     commitments
    0.83
    Activations Density 0.041%

    No Known Activations