© 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. 10-RES-JB
    11. 2852
    Prev
    Next
    INDEX
    Explanations

    symbolic characters and obscure sequences

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     succession
    -0.93
     targeted
    -0.89
     distinguished
    -0.85
     charter
    -0.80
     successive
    -0.80
     differentiated
    -0.79
     constituted
    -0.78
     Mobil
    -0.78
     delegation
    -0.78
     positions
    -0.77
    POSITIVE LOGITS
    ï¸ı
    1.65
    lol
    1.32
    ðŁĺ
    1.31
    shit
    1.28
    ¯
    1.27
    âĿ
    1.20
    ðŁ
    1.20
    fuck
    1.19
    sorry
    1.15
    RIP
    1.14
    Activations Density 0.369%

    No Known Activations