© 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. 4-RES-JB
    11. 24455
    Prev
    Next
    INDEX
    Explanations

    adjectives emphasizing the quality or extent of something

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that convey a positive or strong quality

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

    No Comments

    Negative Logits
    hops
    -0.93
    ults
    -0.87
    ateurs
    -0.87
    iddles
    -0.86
    devices
    -0.86
    lees
    -0.85
    ULTS
    -0.83
    rants
    -0.82
    apps
    -0.82
    units
    -0.78
    POSITIVE LOGITS
     amount
    0.96
     dose
    0.96
     example
    0.91
     antidote
    0.90
     uptick
    0.88
     mixture
    0.87
     distinction
    0.87
     exception
    0.85
     clue
    0.84
     opportunity
    0.83
    Activations Density 0.327%

    No Known Activations