© 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. 1-RES-JB
    11. 15666
    Prev
    Next
    INDEX
    Explanations

    phrases related to enabling or empowering someone or something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "enable" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    boy
    -0.77
     Warcraft
    -0.77
    den
    -0.67
    kaya
    -0.65
    allo
    -0.65
    eal
    -0.65
    child
    -0.63
    ma
    -0.63
    ko
    -0.62
     bite
    -0.62
    POSITIVE LOGITS
     guiActiveUn
    0.96
     enable
    0.90
     enabling
    0.86
    ments
    0.86
     enables
    0.85
    MENTS
    0.83
     confir
    0.82
     enabled
    0.80
    iences
    0.79
     misunder
    0.77
    Activations Density 0.013%

    No Known Activations