© 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. 4-RES-JB
    11. 17001
    Prev
    Next
    INDEX
    Explanations

    proper names containing the sequence "Giorno"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Giovanna" or variations of it

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

    No Comments

    Negative Logits
    */(
    -0.78
    nesday
    -0.75
    tenance
    -0.73
    manship
    -0.73
    stage
    -0.73
    orative
    -0.73
    ioned
    -0.72
    eer
    -0.71
     SPORTS
    -0.69
     Universities
    -0.68
    POSITIVE LOGITS
    Gi
    1.01
    vernment
    0.96
    TeX
    0.94
    olla
    0.94
    ugal
    0.92
    ugi
    0.89
    elin
    0.89
    qs
    0.88
    hetto
    0.87
    quet
    0.85
    Activations Density 0.009%

    No Known Activations