© 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. 7-RES-JB
    11. 17883
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to specific events or entities

    oai_token-act-pair · gpt-3.5-turbo

    significant dates and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hague
    -0.75
    ité
    -0.74
    ĸļ
    -0.70
    initialized
    -0.68
     Donn
    -0.65
     Expect
    -0.65
     Yue
    -0.63
    latest
    -0.61
     Cort
    -0.61
    =~
    -0.61
    POSITIVE LOGITS
     locations
    0.87
     variants
    0.84
     implementations
    0.84
     sightings
    0.83
     cases
    0.83
    pointers
    0.83
     households
    0.82
     varieties
    0.81
     incidents
    0.81
     starters
    0.80
    Activations Density 0.550%

    No Known Activations