© 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. 8-RES-JB
    11. 6074
    Prev
    Next
    INDEX
    Explanations

    keywords related to addiction and treatment

    oai_token-act-pair · gpt-3.5-turbo

    references to addiction and its related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vard
    -0.72
    erial
    -0.72
     Kov
    -0.69
     FIR
    -0.67
    orkshire
    -0.67
    stand
    -0.66
    aber
    -0.65
    telling
    -0.65
    bourg
    -0.64
    eele
    -0.63
    POSITIVE LOGITS
     relapse
    1.00
     addiction
    0.96
     addict
    0.91
     rehab
    0.90
     addicts
    0.85
    encies
    0.81
     addicted
    0.81
     Addiction
    0.80
    icts
    0.80
     stimul
    0.80
    Activations Density 0.057%

    No Known Activations