© 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. 14568
    Prev
    Next
    INDEX
    Explanations

    specific terms starting with 'Dis'

    oai_token-act-pair · gpt-3.5-turbo

    references to "Disqus," a commenting system

    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
    glers
    -0.83
    hetti
    -0.76
     Kinnikuman
    -0.70
     Juliet
    -0.70
     Metatron
    -0.68
    akeru
    -0.68
    DragonMagazine
    -0.67
     Hanna
    -0.64
    imately
    -0.63
    OPLE
    -0.62
    POSITIVE LOGITS
    cipl
    1.13
    ruption
    1.10
    cerning
    1.07
    ciples
    1.06
    qus
    1.06
    placed
    1.04
    enfranch
    1.04
    claimer
    1.02
    rup
    1.01
    plays
    1.00
    Activations Density 0.013%

    No Known Activations