© 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. 11-RES-JB
    11. 5166
    Prev
    Next
    INDEX
    Explanations

    personal experiences or actions in the past tense that are reflective or contemplative in nature

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     millenn
    -0.75
    ILY
    -0.70
    Statement
    -0.67
    ,,,,
    -0.66
    AME
    -0.66
     Worst
    -0.64
    ItemImage
    -0.62
     preferring
    -0.61
     differently
    -0.61
     nevertheless
    -0.61
    POSITIVE LOGITS
     mastered
    0.99
     figured
    0.91
     calmed
    0.87
     established
    0.86
     stabilized
    0.84
     understood
    0.83
     grasped
    0.82
     understand
    0.82
     settled
    0.80
     grasp
    0.80
    Activations Density 0.146%

    No Known Activations