© 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. 3240
    Prev
    Next
    INDEX
    Explanations

    phrases related to prioritizing certain values or interests over others

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to prioritization and the valuing of subjective interests over collective or objective principles

    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
    kan
    -0.82
    aunder
    -0.76
    auri
    -0.75
    alde
    -0.73
    agues
    -0.73
    pez
    -0.72
    estern
    -0.70
    byter
    -0.66
    achusetts
    -0.65
    english
    -0.65
    POSITIVE LOGITS
     aesthetics
    1.01
     profits
    0.99
     quantity
    0.93
     substantive
    0.89
     seriousness
    0.88
     anything
    0.88
     maximizing
    0.87
     mere
    0.87
     actual
    0.87
     ideology
    0.86
    Activations Density 0.253%

    No Known Activations