© 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. 3000
    Prev
    Next
    INDEX
    Explanations

    facts or statistics about various subjects, potentially related to sports, finance, environment, and legal proceedings

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terminology related to measurements and assessments in various contexts

    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
    LT
    -0.65
    CU
    -0.62
    Hop
    -0.62
    DOWN
    -0.61
     contempor
    -0.60
    DIS
    -0.60
    ENE
    -0.60
     bullet
    -0.58
    xtap
    -0.58
     Definitive
    -0.57
    POSITIVE LOGITS
    lems
    1.06
    aughters
    1.05
    ishers
    1.01
    asses
    0.98
    folios
    0.97
    acters
    0.97
    ieties
    0.97
    azines
    0.96
    ables
    0.95
    iors
    0.94
    Activations Density 0.341%

    No Known Activations