© 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. 3366
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of observing or witnessing something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "saw"

    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
    externalActionCode
    -0.73
    trap
    -0.71
    onto
    -0.69
     agric
    -0.68
    currency
    -0.67
    itus
    -0.65
    nesia
    -0.65
    ÃŃa
    -0.62
    hesion
    -0.61
    eware
    -0.61
    POSITIVE LOGITS
    dust
    1.17
     firsthand
    0.99
     glimps
    0.87
    awed
    0.83
     parallels
    0.81
     visions
    0.80
     flashes
    0.77
    saw
    0.77
    lights
    0.76
     similarities
    0.76
    Activations Density 0.086%

    No Known Activations