© 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 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. 9-RES-JB
    11. 15900
    Prev
    Next
    INDEX
    Explanations

    phrases expressing positivity, specifically focusing on "good news."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express positivity or good news

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edIn
    -0.75
    ascript
    -0.68
    ĸļ
    -0.68
    lished
    -0.67
    akeru
    -0.66
     appropriated
    -0.66
    uilding
    -0.65
    structed
    -0.59
    avorite
    -0.59
    20439
    -0.58
    POSITIVE LOGITS
    est
    0.96
     thing
    0.95
    iest
    0.91
    liest
    0.82
     ones
    0.79
     stuff
    0.78
     folks
    0.77
     news
    0.76
     side
    0.76
     ol
    0.75
    Activations Density 0.114%

    No Known Activations