© 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. 12752
    Prev
    Next
    INDEX
    Explanations

    phrases referencing a specific subject and exploring the consequences or implications of that subject

    oai_token-act-pair · gpt-3.5-turbo

    the word "that" in various contexts and forms

    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
    "],"
    -0.78
    rior
    -0.70
    hips
    -0.66
    emis
    -0.62
    016
    -0.62
     Directions
    -0.62
    ãĥĺ
    -0.62
    waters
    -0.61
    kamp
    -0.60
     Pass
    -0.58
    POSITIVE LOGITS
     pesky
    0.99
     fateful
    0.91
     mattered
    0.80
     evening
    0.75
     culminated
    0.74
    cher
    0.73
     kind
    0.73
    eatures
    0.73
     afternoon
    0.71
    ÃĥÃĤ
    0.70
    Activations Density 0.604%

    No Known Activations