© 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. 5367
    Prev
    Next
    INDEX
    Explanations

    phrases indicating controversial or impactful events

    oai_token-act-pair · gpt-3.5-turbo

    the word "That" as a reference point in various contexts

    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
    hops
    -0.85
    ocks
    -0.82
    rypt
    -0.80
    perse
    -0.80
    hin
    -0.79
    cycles
    -0.74
    emis
    -0.74
    paces
    -0.74
    hend
    -0.73
    stals
    -0.73
    POSITIVE LOGITS
     resulted
    1.03
     prompted
    1.03
     fateful
    1.00
     happened
    0.96
     same
    0.95
     sparked
    0.91
     announcement
    0.91
     occurred
    0.89
     amounted
    0.89
     contradicts
    0.89
    Activations Density 0.152%

    No Known Activations