© 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. 0-RES-JB
    11. 20498
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical conditions and treatments, specifically mentioning CBD (Cannabidiol)

    oai_token-act-pair · gpt-3.5-turbo

    references to CBD and related products or topics

    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
     gru
    -0.73
     leve
    -0.70
     insur
    -0.69
     granite
    -0.68
     slope
    -0.68
     mur
    -0.67
     emot
    -0.64
     hier
    -0.63
     grape
    -0.63
     scrimmage
    -0.63
    POSITIVE LOGITS
    BD
    4.34
     BD
    1.89
    bd
    1.75
    BB
    1.54
    DD
    1.52
    BT
    1.38
    BC
    1.38
    BN
    1.37
    BF
    1.35
    CD
    1.33
    Activations Density 0.010%

    No Known Activations