© 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. 15867
    Prev
    Next
    INDEX
    Explanations

    infinitive verbs that indicate a future action or intention

    oai_token-act-pair · gpt-3.5-turbo

    expressions of hopes and aspirations

    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
    IGN
    -0.77
     Warning
    -0.64
    said
    -0.64
    leigh
    -0.63
     versus
    -0.63
    igned
    -0.63
    $$$$
    -0.63
    Choice
    -0.63
     Neck
    -0.62
    orno
    -0.62
    POSITIVE LOGITS
     someday
    1.24
     convince
    1.03
     garner
    1.01
     achieve
    1.00
     persuade
    0.97
     inspire
    0.95
     salvage
    0.95
     attract
    0.93
     alleviate
    0.93
     find
    0.93
    Activations Density 0.108%

    No Known Activations