© 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. 18784
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and gaming, specifically praising certain features or aspects

    oai_token-act-pair · gpt-3.5-turbo

    positive assessments of entertainment media

    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
     Fixed
    -0.67
     apologized
    -0.66
     subsidized
    -0.65
    contact
    -0.64
     inactive
    -0.63
     crappy
    -0.63
     faulty
    -0.63
     Misc
    -0.62
     Progress
    -0.62
     Disabled
    -0.61
    POSITIVE LOGITS
     unforgettable
    1.18
     unmatched
    1.04
     unbeat
    0.97
     unparalleled
    0.95
     mesmer
    0.93
     unmist
    0.92
     irresistible
    0.91
     delight
    0.90
     truly
    0.87
     effortlessly
    0.87
    Activations Density 0.633%

    No Known Activations