© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 2343
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names, especially "Baxter"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific companies or substances related to cannabinoids and their effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ucket
    -0.70
     Vil
    -0.70
    vol
    -0.67
     tennis
    -0.67
     forc
    -0.67
     unequ
    -0.67
     lac
    -0.66
     tun
    -0.65
     ja
    -0.64
     Lithuania
    -0.64
    POSITIVE LOGITS
     CBD
    4.08
     THC
    1.81
     cannabinoids
    1.70
     cannabinoid
    1.60
     cann
    1.47
     dispensary
    1.41
     dispensaries
    1.40
     vape
    1.18
     cannabin
    1.14
     Baxter
    1.10
    Activations Density 0.028%

    No Known Activations