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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 444
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a need or obligation for specific actions or conditions

    oai_token-act-pair · gpt-3.5-turbo

    the word "require" and its various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thal
    -0.81
     loyal
    -0.65
     Hut
    -0.62
     Dod
    -0.62
     Loyal
    -0.62
     Reef
    -0.59
     Lug
    -0.57
     heads
    -0.57
     Jugg
    -0.57
     Universe
    -0.57
    POSITIVE LOGITS
     require
    3.36
    require
    2.53
     requires
    2.22
     requiring
    1.94
    requires
    1.78
     required
    1.61
     involve
    1.57
     Requires
    1.47
     entail
    1.46
     rely
    1.46
    Activations Density 0.016%

    No Known Activations