© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 17432
    Prev
    Next
    INDEX
    Explanations

    phrases related to leadership, protection, and guidance towards a better life

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to guidance and support in life

    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
    MX
    -0.75
    iannopoulos
    -0.73
     CIS
    -0.73
    classified
    -0.72
    umpy
    -0.72
     Stephenson
    -0.72
    assic
    -0.72
    ampunk
    -0.71
     Murdoch
    -0.70
     Coulter
    -0.68
    POSITIVE LOGITS
     righteousness
    1.39
     repentance
    1.26
     piety
    1.22
     humility
    1.20
     goodness
    1.18
     heavenly
    1.13
     Heavenly
    1.13
     salvation
    1.12
     virtuous
    1.12
    leness
    1.12
    Activations Density 0.339%

    No Known Activations