© 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. 8-RES-JB
    11. 6285
    Prev
    Next
    INDEX
    Explanations

    sentences expressing appreciation or recognition

    oai_token-act-pair · gpt-3.5-turbo

    expressions of appreciation and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     filler
    -0.79
     tack
    -0.79
     inverse
    -0.77
     magnetic
    -0.74
     elusive
    -0.74
     phantom
    -0.73
     interpol
    -0.73
     spinning
    -0.73
     pir
    -0.72
     unexpl
    -0.72
    POSITIVE LOGITS
    Thank
    1.44
    Therefore
    1.16
    Tonight
    1.12
    Govern
    1.10
    Chair
    1.04
    Please
    1.02
    Today
    1.01
    Article
    0.99
    Upon
    0.98
    Peace
    0.97
    Activations Density 0.410%

    No Known Activations