© 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. 7-RES-JB
    11. 15322
    Prev
    Next
    INDEX
    Explanations

    verbs in the infinitive form that indicate the need for action or decision-making

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating obligations or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Recommended
    -0.77
    Luc
    -0.68
    Friend
    -0.66
    Mem
    -0.62
     Glad
    -0.62
     Ambro
    -0.62
     Stanton
    -0.62
     Ideal
    -0.62
     Lar
    -0.62
    interstitial
    -0.61
    POSITIVE LOGITS
     rethink
    1.09
     wait
    1.06
     settle
    0.90
     reconsider
    0.89
     fend
    0.86
     rely
    0.85
     endure
    0.85
     revise
    0.85
     reckon
    0.83
     overcome
    0.82
    Activations Density 0.078%

    No Known Activations