© 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. 9-RES-JB
    11. 7010
    Prev
    Next
    INDEX
    Explanations

    opinions or statements regarding the legality or social acceptance of certain practices or substances, specifically related to the topic of marijuana

    oai_token-act-pair · gpt-3.5-turbo

    opinions and statistics related to legalization, particularly on contentious issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Saga
    -0.67
     Gentleman
    -0.59
     Grail
    -0.58
     Mug
    -0.58
     spirited
    -0.58
    Scene
    -0.58
     Rampage
    -0.58
     Chess
    -0.55
    tick
    -0.55
     Letter
    -0.54
    POSITIVE LOGITS
     placebo
    0.96
     thereafter
    0.82
    iliate
    0.81
     altogether
    0.81
    %).
    0.74
    ocry
    0.74
     respectively
    0.74
    ).[
    0.72
     unspecified
    0.71
     outright
    0.70
    Activations Density 0.707%

    No Known Activations