© 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. 8-RES-JB
    11. 8956
    Prev
    Next
    INDEX
    Explanations

    weather-related information, particularly high and low temperatures

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to weather and environmental conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rompt
    -0.81
    uez
    -0.77
    iqu
    -0.76
    itely
    -0.75
    uder
    -0.72
    ippi
    -0.71
    undai
    -0.71
    ubi
    -0.71
    azo
    -0.70
    Ó
    -0.70
    POSITIVE LOGITS
     Appears
    1.34
     Played
    1.04
     Uses
    1.04
     Includes
    1.04
     Contains
    0.98
     Provides
    0.98
     Started
    0.94
     Became
    0.93
     Comes
    0.92
     Needs
    0.92
    Activations Density 0.599%

    No Known Activations