© 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. 10-RES-JB
    11. 10163
    Prev
    Next
    INDEX
    Explanations

    phrases related to causes and effects

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating economic impacts or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idelines
    -0.77
    poon
    -0.67
    uno
    -0.65
    don
    -0.64
    song
    -0.63
     Technique
    -0.63
    esian
    -0.62
    odd
    -0.61
     Recommended
    -0.61
     Concept
    -0.61
    POSITIVE LOGITS
     untold
    1.18
     billions
    1.15
     millions
    1.12
     fewer
    1.07
     trillions
    1.05
     thousands
    1.01
     poorer
    0.96
     hundreds
    0.95
     savings
    0.93
     wealthier
    0.92
    Activations Density 0.338%

    No Known Activations