© 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. 4-RES-JB
    11. 14732
    Prev
    Next
    INDEX
    Explanations

    references to the drug "OxyContin" or similar oxy compounds

    oai_token-act-pair · gpt-3.5-turbo

    references to the opioid Oxycodone and related substances

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

    No Comments

    Negative Logits
    fulness
    -0.86
    nesota
    -0.82
    heit
    -0.78
    */(
    -0.75
    ista
    -0.75
     guiActiveUnfocused
    -0.74
    tenance
    -0.72
    erers
    -0.72
     behavi
    -0.70
    HCR
    -0.70
    POSITIVE LOGITS
    zzy
    0.94
     Oxy
    0.91
    toc
    0.90
    mor
    0.86
    gen
    0.85
    Contin
    0.84
    xy
    0.80
    gyn
    0.80
    eah
    0.78
    uba
    0.74
    Activations Density 0.019%

    No Known Activations