© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9394
    Prev
    Next
    INDEX
    Explanations

    terms related to artificial intelligence and machine learning

    oai_token-act-pair · gpt-3.5-turbo

    references to artificial intelligence and machine learning technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    76561
    -0.75
    inness
    -0.75
    20439
    -0.74
    mitt
    -0.73
    ãĥĥãĥī
    -0.73
    Travel
    -0.71
    ¦
    -0.71
     earthqu
    -0.71
    emate
    -0.70
    ãĥ´
    -0.69
    POSITIVE LOGITS
     technologies
    1.65
     technology
    1.53
     techniques
    1.39
     algorithms
    1.30
     capabilities
    1.29
     platforms
    1.26
     devices
    1.25
     solutions
    1.24
     Technologies
    1.23
     systems
    1.22
    Activations Density 0.178%

    No Known Activations