© 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. 2-RES-JB
    11. 506
    Prev
    Next
    INDEX
    Explanations

    the adjective "valuable"

    oai_token-act-pair · gpt-4-turbo

    Keywords related to value, importance, and lessons

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of value or worth

    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
    annis
    -0.80
    thus
    -0.74
    abi
    -0.72
    sein
    -0.71
    ilk
    -0.70
    abad
    -0.69
    nature
    -0.69
    ulhu
    -0.68
    peak
    -0.68
    adal
    -0.67
    POSITIVE LOGITS
     asset
    0.94
     valuable
    0.91
    uable
    0.85
     trove
    0.82
     distingu
    0.81
     proposition
    0.79
     retri
    0.77
     assets
    0.77
     veter
    0.75
     propositions
    0.74
    Activations Density 0.006%

    No Known Activations