© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16887
    Prev
    Next
    INDEX
    Explanations

    text containing the word "Juju"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "ju."

    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
    tons
    -0.80
     Grain
    -0.69
     Orbit
    -0.67
     Regulations
    -0.67
     Ninth
    -0.66
    Aut
    -0.65
     Continental
    -0.64
     Flight
    -0.64
     Spectrum
    -0.64
     Horizons
    -0.63
    POSITIVE LOGITS
    xtap
    1.33
    ju
    1.29
    avascript
    0.98
    ipers
    0.97
    ulkan
    0.94
    undai
    0.93
    arez
    0.93
    ppa
    0.92
    awei
    0.91
    udeau
    0.90
    Activations Density 0.007%

    No Known Activations