© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 16451
    Prev
    Next
    INDEX
    Explanations

    terms related to the compound Cannabidiol (CBD)

    oai_token-act-pair · gpt-3.5-turbo

    references to cannabidiol (CBD) and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    afort
    -0.76
    FTWARE
    -0.74
    metry
    -0.73
    ittee
    -0.68
    zanne
    -0.63
    atern
    -0.62
    interface
    -0.62
    lled
    -0.62
    vern
    -0.62
    porary
    -0.61
    POSITIVE LOGITS
    NF
    1.10
    BD
    1.03
     BD
    0.92
    ishop
    0.84
    YL
    0.80
    urst
    0.78
    ridges
    0.77
    Ħ¢
    0.76
    ranch
    0.74
    ionics
    0.74
    Activations Density 0.009%

    No Known Activations