© 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. 3722
    Prev
    Next
    INDEX
    Explanations

    mentions of smoking or related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to smoking and its effects

    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
    assian
    -0.86
     Vector
    -0.78
    ngth
    -0.69
     Defenders
    -0.68
    ensional
    -0.68
    translation
    -0.68
    HCR
    -0.67
    ousse
    -0.66
     Ake
    -0.65
     Nou
    -0.65
    POSITIVE LOGITS
     cessation
    1.36
     smoking
    1.19
     cigarettes
    1.12
     smoker
    1.11
     smoked
    1.07
     smoke
    1.02
     cigars
    0.99
     smokers
    0.95
     habits
    0.94
     cig
    0.91
    Activations Density 0.013%

    No Known Activations