© 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. 960
    Prev
    Next
    INDEX
    Explanations

    phrases related to controversial or sensational news stories

    oai_token-act-pair · gpt-3.5-turbo

    sentences or statements that discuss significant events or issues

    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
     defe
    -0.86
     bud
    -0.74
     bounded
    -0.72
     affili
    -0.69
     appra
    -0.67
     medium
    -0.66
     clin
    -0.65
     dep
    -0.65
     uncom
    -0.65
     rebirth
    -0.64
    POSITIVE LOGITS
     Similarly
    1.19
     Needless
    1.14
     Likewise
    1.12
     Apparently
    1.09
     Specifically
    1.07
     Previously
    1.05
     Interestingly
    1.05
     Similar
    1.04
     Whereas
    1.04
     Ironically
    1.03
    Activations Density 0.757%

    No Known Activations