© 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. 3-RES-JB
    11. 23781
    Prev
    Next
    INDEX
    Explanations

    references to names of people and places, particularly in the context of news or events

    oai_token-act-pair · gpt-3.5-turbo

    references to North Korean leaders and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NIGHT
    -0.80
     Conv
    -0.76
     Alleg
    -0.73
     Frenzy
    -0.72
     cort
    -0.70
     Acqu
    -0.69
     Demons
    -0.69
     Phillies
    -0.68
     msec
    -0.67
     Colossus
    -0.66
    POSITIVE LOGITS
    jiang
    1.24
    hua
    1.17
    ijing
    1.16
     Yuan
    1.15
    wei
    1.14
    Hong
    1.14
    jin
    1.13
     Jiang
    1.11
     Hua
    1.10
     Cheng
    1.09
    Activations Density 0.251%

    No Known Activations