© 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. 22291
    Prev
    Next
    INDEX
    Explanations

    phrases related to active participation or involvement in various activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "actively" and its contexts

    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
    ethy
    -0.77
    eways
    -0.76
    ottage
    -0.71
     finally
    -0.71
    itionally
    -0.71
     Aura
    -0.66
    vity
    -0.66
    llan
    -0.65
    inally
    -0.64
     Awakens
    -0.63
    POSITIVE LOGITS
     pursuing
    1.22
     involved
    1.10
     engaged
    1.07
     seeking
    1.04
     trying
    1.04
     researching
    1.03
     exploring
    1.01
     attempting
    1.01
     searching
    1.01
     contemplating
    0.99
    Activations Density 0.116%

    No Known Activations