© 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. 6-RES-JB
    11. 604
    Prev
    Next
    INDEX
    Explanations

    phrases related to evaluation, judgment, or recommendation towards a positive or negative outcome

    oai_token-act-pair · gpt-3.5-turbo

    expressions of judgment regarding quality or suitability

    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
    beit
    -0.73
     Neuroscience
    -0.64
     Heath
    -0.62
    rather
    -0.62
    bery
    -0.61
    achine
    -0.61
    alm
    -0.61
     irresist
    -0.60
    ription
    -0.59
     Enabled
    -0.59
    POSITIVE LOGITS
     anymore
    1.35
     nor
    0.94
    ÙIJ
    0.79
    ãĤ®
    0.79
    Ö¼
    0.78
    èª
    0.76
    Ú
    0.74
    à¤
    0.72
     yet
    0.70
    à¦
    0.68
    Activations Density 0.580%

    No Known Activations