© 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. 2595
    Prev
    Next
    INDEX
    Explanations

    phrases involving written documents or agreements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "written" in various contexts

    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
    tics
    -0.85
    ertodd
    -0.84
    alian
    -0.82
    alos
    -0.81
    apo
    -0.81
    nels
    -0.81
    cius
    -0.81
    olit
    -0.80
    rir
    -0.78
    hov
    -0.77
    POSITIVE LOGITS
     agreement
    1.06
     submission
    1.00
     correspondence
    0.99
     message
    0.95
     consent
    0.95
     presentation
    0.95
     acknowledgement
    0.94
     communication
    0.92
     acknowledgment
    0.91
     permission
    0.91
    Activations Density 0.101%

    No Known Activations