© 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. 2-RES-JB
    11. 17350
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparison or contrast

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ccess
    -0.82
    load
    -0.73
    ciating
    -0.70
    corn
    -0.70
    gging
    -0.69
    access
    -0.65
    duct
    -0.65
    Anonymous
    -0.64
    ça
    -0.64
    cham
    -0.62
    POSITIVE LOGITS
     reflect
    1.06
     reflections
    1.06
     reflecting
    0.99
     reflects
    0.96
     reflection
    0.94
     reflected
    0.93
    reflect
    0.91
     Reflect
    0.85
     shards
    0.75
    ively
    0.75
    Activations Density 0.014%

    No Known Activations