© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16082
    Prev
    Next
    INDEX
    Explanations

    phrases related to leadership and authority

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "the" 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
    ially
    -0.81
    rics
    -0.78
    affiliated
    -0.78
    untarily
    -0.74
    EH
    -0.71
    iculty
    -0.71
    accompanied
    -0.71
    members
    -0.70
    Contact
    -0.70
    atively
    -0.70
    POSITIVE LOGITS
     apocalypse
    1.17
     abyss
    1.10
     heavens
    1.07
     afterlife
    1.03
     cosmos
    1.02
     iceberg
    1.00
     universe
    0.99
     proverbial
    0.97
     devil
    0.96
     imagination
    0.95
    Activations Density 0.423%

    No Known Activations