© 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. 8-RES-JB
    11. 2092
    Prev
    Next
    INDEX
    Explanations

    triggers related to the start of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "When."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.72
    ding
    -0.70
    kaya
    -0.66
    whatever
    -0.65
    agin
    -0.65
    zzi
    -0.64
    udder
    -0.64
    \\\\\\\\
    -0.62
    aking
    -0.62
    åĤ
    -0.62
    POSITIVE LOGITS
    soever
    1.23
     asked
    1.05
     confronted
    1.01
     pressed
    0.93
     faced
    0.92
    ce
    0.90
     contacted
    0.82
     questioned
    0.79
     viewed
    0.78
     designing
    0.72
    Activations Density 0.090%

    No Known Activations