© 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. 10-RES-JB
    11. 3159
    Prev
    Next
    INDEX
    Explanations

    percentage changes or fluctuations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significant decreases or increases, particularly with numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngth
    -0.71
    finished
    -0.70
    Finish
    -0.68
    itialized
    -0.66
    jad
    -0.65
    hid
    -0.64
    psc
    -0.62
    rar
    -0.62
    aine
    -0.61
    ollo
    -0.61
    POSITIVE LOGITS
     leaps
    1.25
     fractions
    0.98
     approximately
    0.96
     20
    0.94
     25
    0.93
     50
    0.92
     roughly
    0.91
     trillions
    0.90
     nearly
    0.90
     15
    0.89
    Activations Density 0.063%

    No Known Activations