© 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. 9-RES-JB
    11. 9894
    Prev
    Next
    INDEX
    Explanations

    the word "bunch" appearing in the text

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "bunch."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Advocate
    -0.70
     Correspond
    -0.61
    âĢ¢âĢ¢
    -0.58
     Breed
    -0.54
     resonance
    -0.54
     passage
    -0.54
    mediate
    -0.53
     Conversation
    -0.53
     breathed
    -0.52
    agate
    -0.52
    POSITIVE LOGITS
     of
    0.98
    alions
    0.81
    ubs
    0.80
    icles
    0.79
    istical
    0.78
    fuck
    0.78
    rats
    0.78
    atical
    0.77
    acky
    0.74
    asses
    0.74
    Activations Density 0.038%

    No Known Activations