© 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. 7-RES-JB
    11. 23093
    Prev
    Next
    INDEX
    Explanations

    phrases indicating preparation or readiness

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "preparing for."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ware
    -0.77
    taboola
    -0.72
    ï¸ı
    -0.72
    cles
    -0.72
    hai
    -0.72
    notation
    -0.70
    eps
    -0.70
    rf
    -0.67
    weed
    -0.66
    gnu
    -0.64
    POSITIVE LOGITS
     conting
    1.21
     eviction
    0.84
     emergencies
    0.83
     contingency
    0.83
     impending
    0.81
     future
    0.80
     takeoff
    0.79
     passage
    0.78
     tomorrow
    0.78
     battle
    0.76
    Activations Density 0.095%

    No Known Activations