© 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. 6-RES-JB
    11. 14713
    Prev
    Next
    INDEX
    Explanations

    adverbs intensifying the degree of something

    oai_token-act-pair · gpt-3.5-turbo

    emphasized adjectives and adverbs that express intensity or degree

    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
    agents
    -0.85
     Challenges
    -0.78
    rencies
    -0.77
     Loans
    -0.74
     waivers
    -0.73
    lees
    -0.71
     Contracts
    -0.71
     GEAR
    -0.70
     Extensions
    -0.69
    eeds
    -0.69
    POSITIVE LOGITS
     cohesive
    0.80
     sizable
    0.79
     wide
    0.79
     diverse
    0.77
     narrow
    0.76
     uphill
    0.75
     disproportionate
    0.75
     representative
    0.74
     comprehensive
    0.74
     similar
    0.74
    Activations Density 0.086%

    No Known Activations