© 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. 16011
    Prev
    Next
    INDEX
    Explanations

    mentions of medications, particularly those related to pain management such as opioids

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the substance "oxy" and its relation to various contexts

    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
    */(
    -0.93
    HCR
    -0.88
    fulness
    -0.82
    istically
    -0.77
    erers
    -0.76
    tenance
    -0.75
     à¨
    -0.74
    istics
    -0.72
    ista
    -0.72
    hips
    -0.71
    POSITIVE LOGITS
    toc
    1.01
     Oxy
    0.99
    mor
    0.96
     oxy
    0.94
    cod
    0.85
     opioid
    0.84
    oxy
    0.84
    gee
    0.84
    Contin
    0.82
     narc
    0.81
    Activations Density 0.005%

    No Known Activations