© 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. 7926
    Prev
    Next
    INDEX
    Explanations

    contrasts between two different things or concepts

    oai_token-act-pair · gpt-3.5-turbo

    the word "whereas" or its variants, indicating contrast or comparison

    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
    hal
    -0.86
    entry
    -0.85
    aer
    -0.79
    osal
    -0.79
    urious
    -0.73
    hack
    -0.71
    bard
    -0.69
    Roll
    -0.69
    orc
    -0.69
    ve
    -0.69
    POSITIVE LOGITS
    xual
    1.01
    soever
    0.80
    BILITIES
    0.79
    lihood
    0.74
     CLIENT
    0.72
    wcsstore
    0.67
    sembly
    0.67
     disadvant
    0.66
    */(
    0.66
     browsing
    0.66
    Activations Density 0.007%

    No Known Activations