© 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. 0-RES-JB
    11. 6579
    Prev
    Next
    INDEX
    Explanations

    terms related to computing workloads or backlogs

    oai_token-act-pair · gpt-3.5-turbo

    terms related to workloads and processing demands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rouge
    -0.76
    Liber
    -0.68
    ade
    -0.66
     escaped
    -0.65
    formed
    -0.63
    ought
    -0.63
    reve
    -0.62
     Signs
    -0.61
    na
    -0.61
    asin
    -0.60
    POSITIVE LOGITS
     workload
    3.94
     backlog
    1.53
     workflow
    1.33
     throughput
    1.29
     load
    1.27
     burden
    1.11
     chores
    1.08
     filesystem
    1.05
     lapt
    1.05
     burdens
    1.03
    Activations Density 0.019%

    No Known Activations