© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 7313
    Prev
    Next
    INDEX
    Explanations

    words related to addiction

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to addiction

    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
    vard
    -0.73
    orkshire
    -0.71
    erial
    -0.71
    eele
    -0.67
    telling
    -0.66
    asonic
    -0.66
     Kov
    -0.66
    weather
    -0.66
    aber
    -0.64
    atche
    -0.64
    POSITIVE LOGITS
     relapse
    1.01
     addiction
    0.93
     rehab
    0.92
     addict
    0.90
     Addiction
    0.82
     addicted
    0.82
     addicts
    0.81
     rehabilitation
    0.79
     disorder
    0.78
    itute
    0.78
    Activations Density 0.082%

    No Known Activations