© 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. 17050
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal accomplishments and experiences

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their professional achievements or roles

    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
    wake
    -0.79
    uating
    -0.67
    acceptable
    -0.67
    uation
    -0.62
     Recap
    -0.60
    click
    -0.60
    seless
    -0.58
    arter
    -0.58
    abus
    -0.58
    truth
    -0.57
    POSITIVE LOGITS
     been
    1.21
     toured
    1.03
     participated
    1.03
    been
    1.02
     collaborated
    1.01
     teamed
    1.00
     battled
    1.00
     undergone
    0.99
     amassed
    0.99
     worked
    0.99
    Activations Density 0.268%

    No Known Activations