© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 4373
    Prev
    Next
    INDEX
    Explanations

    computer code snippets

    oai_token-act-pair · gpt-3.5-turbo

    references to video game features and updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abwe
    -0.77
     lifes
    -0.74
     volunteered
    -0.72
    ÃŃs
    -0.70
    heit
    -0.67
    hower
    -0.67
    ewater
    -0.67
     intervened
    -0.67
     assignment
    -0.65
     Twain
    -0.64
    POSITIVE LOGITS
    Meanwhile
    1.07
    Speaking
    1.07
    Advertisement
    1.02
    Elsewhere
    1.00
    Rum
    1.00
    Exit
    0.99
    Samsung
    0.98
    Interestingly
    0.96
    Sony
    0.94
    Hardware
    0.93
    Activations Density 0.469%

    No Known Activations