© 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. 9-RES-JB
    11. 17093
    Prev
    Next
    INDEX
    Explanations

    Italian names

    oai_token-act-pair · gpt-3.5-turbo

    Italian names and cultural references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    teenth
    -0.92
    older
    -0.87
    earchers
    -0.83
    eer
    -0.82
    vana
    -0.80
    waukee
    -0.79
    eeper
    -0.79
    ority
    -0.77
    keyes
    -0.77
    essee
    -0.76
    POSITIVE LOGITS
     Marino
    1.00
     Petro
    0.96
     Rossi
    0.96
     Pic
    0.93
     Fran
    0.87
     Bos
    0.86
     Russo
    0.86
     Perez
    0.85
     Camb
    0.85
     Bor
    0.85
    Activations Density 0.124%

    No Known Activations