© 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. 0-RES-JB
    11. 4156
    Prev
    Next
    INDEX
    Explanations

    words related to various types of addiction

    oai_token-act-pair · gpt-3.5-turbo

    references to different types of addiction and related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heet
    -0.78
    semb
    -0.68
    semble
    -0.67
     Yard
    -0.67
    ÄŁ
    -0.65
    Spe
    -0.64
    ruce
    -0.64
     tall
    -0.62
    tall
    -0.61
     Mous
    -0.61
    POSITIVE LOGITS
     addiction
    3.61
     Addiction
    2.92
     addicts
    2.53
     addict
    2.39
     addicted
    2.35
     addictive
    2.18
     alcoholism
    1.92
     overdose
    1.92
     overdoses
    1.70
     relapse
    1.61
    Activations Density 0.020%

    No Known Activations