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

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 24047
    Prev
    Next
    INDEX
    Explanations

    mentions of cannabis or marijuana-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to marijuana or cannabis culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     livest
    -0.75
     simultane
    -0.72
    IGH
    -0.70
     obser
    -0.69
     Hitman
    -0.66
     silence
    -0.64
     distingu
    -0.63
    -+
    -0.61
     Prosecut
    -0.61
     mosqu
    -0.61
    POSITIVE LOGITS
    pour
    1.36
    tery
    1.29
    luck
    1.21
    assium
    1.12
    atoes
    1.04
    ting
    1.04
    bell
    1.03
    tering
    0.98
    entially
    0.95
    atos
    0.93
    Activations Density 0.019%

    No Known Activations