© 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. 16096
    Prev
    Next
    INDEX
    Explanations

    terms related to cooperation or working together

    oai_token-act-pair · gpt-3.5-turbo

    references to cooperative efforts or collaborations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Brah
    -0.73
     Faul
    -0.69
     Fitzgerald
    -0.67
     context
    -0.67
     Flam
    -0.65
     caveats
    -0.64
     Tant
    -0.64
     Slim
    -0.64
     complex
    -0.63
     concess
    -0.63
    POSITIVE LOGITS
    founder
    1.41
    ordinate
    1.39
    operative
    1.38
    authored
    1.35
    workers
    1.28
    operation
    1.27
    worker
    1.25
    ord
    1.23
    existence
    1.23
    opted
    1.21
    Activations Density 0.035%

    No Known Activations