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

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 3398
    Prev
    Next
    INDEX
    Explanations

    the word "ina" or variations of the name "ina"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Dina."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yright
    -0.88
    geoning
    -0.77
    matically
    -0.76
    nesday
    -0.75
    ansas
    -0.72
    NING
    -0.72
    acular
    -0.70
    nard
    -0.69
    pelled
    -0.69
    rosse
    -0.67
    POSITIVE LOGITS
    fter
    1.00
    BILITY
    0.90
     Fey
    0.88
    cious
    0.85
     Jol
    0.85
    eus
    0.84
     Rica
    0.83
    udi
    0.83
    ppa
    0.82
    ux
    0.82
    Activations Density 0.050%

    No Known Activations