© 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. 2-RES-JB
    11. 17460
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific cannabinoid compound, likely tetrahydrocannabinol (THC)

    oai_token-act-pair · gpt-3.5-turbo

    references to "tetra" or "tetrahedrons" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģĦ
    -0.87
    士
    -0.86
    nesota
    -0.81
    é¾įåĸļ士
    -0.79
     Marketable
    -0.78
    CVE
    -0.72
    FontSize
    -0.72
    éĹĺ
    -0.71
    FUL
    -0.68
    ãģĭ
    -0.65
    POSITIVE LOGITS
     tet
    1.12
    hered
    1.07
    anus
    1.07
    oxin
    0.94
    ronics
    0.92
    rop
    0.90
    rod
    0.89
     Tet
    0.88
    anic
    0.88
    rell
    0.88
    Activations Density 0.005%

    No Known Activations