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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6-RES-JB
    11. 19696
    Prev
    Next
    INDEX
    Explanations

    phrases related to political figures and government activities

    oai_token-act-pair · gpt-3.5-turbo

    references to legal agreements and judicial proceedings

    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
     Whitman
    -0.82
     favored
    -0.76
    avored
    -0.75
    GOP
    -0.74
    Defense
    -0.74
     favors
    -0.73
     nonprofits
    -0.73
    colored
    -0.73
     Hawai
    -0.72
     behaviors
    -0.72
    POSITIVE LOGITS
     £
    1.32
     recognise
    1.31
     centre
    1.28
     realise
    1.27
     apologise
    1.23
     apologised
    1.18
     analyse
    1.17
     Labour
    1.16
     criticised
    1.16
     organising
    1.15
    Activations Density 2.999%

    No Known Activations