© 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. 4-RES-JB
    11. 6898
    Prev
    Next
    INDEX
    Explanations

    the word "be" with high activation values

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "be" in various contexts

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

    No Comments

    Negative Logits
     Harlem
    -0.64
    ablishment
    -0.62
     guarantee
    -0.60
    ision
    -0.60
     Elise
    -0.59
     Mund
    -0.58
     Stain
    -0.58
    orer
    -0.58
    shall
    -0.57
     Must
    -0.57
    POSITIVE LOGITS
     forgiven
    1.03
     able
    0.94
     mistaken
    0.91
    acons
    0.90
     construed
    0.87
     tempted
    0.83
    heading
    0.79
     considered
    0.79
     regarded
    0.78
     underestimated
    0.77
    Activations Density 0.148%

    No Known Activations