© 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. 6878
    Prev
    Next
    INDEX
    Explanations

    phrases related to various topics and subjects, potentially from different genres like television shows, movies, politics, and personal reflections

    oai_token-act-pair · gpt-3.5-turbo
    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
     manif
    -0.96
     Vaugh
    -0.89
    geries
    -0.77
     vulner
    -0.76
     fronts
    -0.76
     lawy
    -0.76
     harness
    -0.76
     levers
    -0.75
     manifold
    -0.72
     prolifer
    -0.71
    POSITIVE LOGITS
    ï¸ı
    1.29
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    1.03
    âĶĢâĶĢâĶĢâĶĢ
    1.00
    STAR
    0.97
    âĸ¬âĸ¬
    0.94
    FIN
    0.94
    ש
    0.90
    âĸ
    0.89
    cffffcc
    0.89
    âĸł
    0.88
    Activations Density 0.062%

    No Known Activations