© 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. 9-RES-JB
    11. 15653
    Prev
    Next
    INDEX
    Explanations

    instructions or commands focusing on physical actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to decision-making and taking action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TION
    -0.92
     proble
    -0.76
    requ
    -0.76
    nown
    -0.74
    ItemThumbnailImage
    -0.73
     Pwr
    -0.70
    etheless
    -0.68
    yssey
    -0.68
    ĺħ
    -0.67
    DragonMagazine
    -0.67
    POSITIVE LOGITS
     chairs
    1.21
     torches
    1.16
     desks
    1.14
     benches
    1.11
     pipes
    0.99
     typew
    0.99
     bricks
    0.98
     keyboards
    0.97
     shovel
    0.97
     knives
    0.97
    Activations Density 0.730%

    No Known Activations