© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3860
    Prev
    Next
    INDEX
    Explanations

    mentions of military-related activities and equipment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "and" related to various environmental and ecological topics

    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
    unda
    -0.80
    é¾įå¥ij士
    -0.76
     Rosenberg
    -0.70
     Ambro
    -0.70
     Ratings
    -0.69
    tone
    -0.67
    iane
    -0.67
    ruary
    -0.66
     Radical
    -0.65
     Transparency
    -0.65
    POSITIVE LOGITS
     trucks
    1.14
     helicopters
    1.05
     motorcycles
    1.04
     amphib
    1.02
     bicycles
    1.02
     pedestrians
    1.01
     dolphins
    0.98
     horses
    0.98
     airplanes
    0.96
     submarines
    0.96
    Activations Density 0.295%

    No Known Activations