© 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 EvalsExportsinterp-engineNEWAPI 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. 5153
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific references such as poll results, court opinions, media analysis, and official themes

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to polling and political context

    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
     vain
    -0.78
     republican
    -0.73
     knit
    -0.61
    iannopoulos
    -0.60
     needles
    -0.59
    Downloadha
    -0.59
     crochet
    -0.58
     bake
    -0.58
     shave
    -0.58
     bulk
    -0.58
    POSITIVE LOGITS
     Works
    0.87
     Manager
    0.87
     Room
    0.85
     Week
    0.84
     Authority
    0.82
     Month
    0.82
     Corps
    0.80
     Blocks
    0.80
    Co
    0.80
     Accountability
    0.80
    Activations Density 0.598%

    No Known Activations