© 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. 545
    Prev
    Next
    INDEX
    Explanations

    words related to controversies or legal issues

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of the word "quarantine" and related concepts

    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
     resemb
    -0.77
    ngth
    -0.67
     tight
    -0.64
     suggestive
    -0.64
    DragonMagazine
    -0.64
     resemblance
    -0.61
    76561
    -0.61
     slee
    -0.60
     stub
    -0.59
     fructose
    -0.59
    POSITIVE LOGITS
    itely
    0.88
    ocally
    0.88
    ional
    0.86
    arine
    0.84
    bush
    0.82
    ilogy
    0.82
    fecture
    0.79
    rences
    0.78
    idian
    0.77
    agonist
    0.74
    Activations Density 0.065%

    No Known Activations