© 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. 0-RES-JB
    11. 10312
    Prev
    Next
    INDEX
    Explanations

    adjectives describing something extraordinary or impressive

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "stunning" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ops
    -0.71
    ends
    -0.71
    ership
    -0.70
    iability
    -0.66
    li
    -0.66
    pps
    -0.66
    thren
    -0.65
    ied
    -0.64
    ii
    -0.64
    ief
    -0.64
    POSITIVE LOGITS
     stunning
    3.43
     breathtaking
    2.35
     startling
    1.83
     astonishing
    1.79
     spectacular
    1.77
     astounding
    1.77
     gorgeous
    1.74
     shocking
    1.73
     dazzling
    1.69
     staggering
    1.65
    Activations Density 0.020%

    No Known Activations