© 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
    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. 17317
    Prev
    Next
    INDEX
    Explanations

    terms or phrases representing essential, commonly used items or practices

    oai_token-act-pair · gpt-3.5-turbo

    mentions of staple foods or essential items in various contexts

    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
    odore
    -0.95
    vernment
    -0.85
    apego
    -0.79
    TPPStreamerBot
    -0.78
    hani
    -0.77
    hap
    -0.77
    zbollah
    -0.74
    oping
    -0.73
    sterdam
    -0.72
    cember
    -0.72
    POSITIVE LOGITS
     staple
    0.98
     staples
    0.94
    stay
    0.87
    ãĥ¢
    0.75
    essential
    0.74
    ãĥij
    0.74
    tenance
    0.73
     foods
    0.72
    é¾įå¥ij士
    0.72
    weights
    0.70
    Activations Density 0.014%

    No Known Activations