© 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. 10-RES-JB
    11. 20620
    Prev
    Next
    INDEX
    Explanations

    words related to societal structure and functions, such as 'function', 'become', 'thrive', 'vulnerable', 'collapse', 'rigged', 'market', 'relevant', 'anomal..

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to authority and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eyebrow
    -0.80
     flurry
    -0.75
     motions
    -0.71
     overheard
    -0.69
     confir
    -0.67
     vomiting
    -0.66
     groin
    -0.66
     guesses
    -0.66
     glances
    -0.62
     shenan
    -0.62
    POSITIVE LOGITS
     economically
    1.00
     Its
    0.99
     fundamentally
    0.99
     itself
    0.98
     geographically
    0.97
     internationally
    0.95
     its
    0.94
     globally
    0.94
     insofar
    0.93
    Its
    0.93
    Activations Density 0.607%

    No Known Activations