© 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. 12434
    Prev
    Next
    INDEX
    Explanations

    items that come in pairs or have two different options

    oai_token-act-pair · gpt-3.5-turbo

    instances of categorization and classification into two groups or types

    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
     certs
    -0.83
    enger
    -0.76
    board
    -0.70
     lett
    -0.67
    phi
    -0.64
     nowhere
    -0.62
     rattled
    -0.61
    endon
    -0.61
    odo
    -0.60
    ¬¼
    -0.60
    POSITIVE LOGITS
     namely
    1.06
     Firstly
    0.95
     viz
    0.87
    Firstly
    0.73
     sexes
    0.70
    hemat
    0.68
     ones
    0.64
     Olson
    0.61
    avorite
    0.61
     Wink
    0.61
    Activations Density 0.234%

    No Known Activations