© 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 EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 16377
    Prev
    Next
    INDEX
    Explanations

    mentions of psychoactive substances or activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to psychoactive substances and their effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esan
    -0.89
    aneers
    -0.83
    «ĺ
    -0.82
    unts
    -0.82
    è£ħ
    -0.78
    ¬¼
    -0.74
    adra
    -0.73
     ç¥ŀ
    -0.72
    Ń·
    -0.72
    hner
    -0.71
    POSITIVE LOGITS
    uated
    0.82
    ibility
    0.82
    uating
    0.79
    uates
    0.79
    active
    0.77
    iveness
    0.77
     ingredient
    0.75
    uation
    0.74
    imental
    0.73
    ãĤ¿
    0.73
    Activations Density 0.008%

    No Known Activations