© 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. 9-RES-JB
    11. 15490
    Prev
    Next
    INDEX
    Explanations

    the word "be" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases beginning with "don't be."

    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
    inally
    -0.86
    yip
    -0.84
     Enhancement
    -0.75
    ciation
    -0.73
     hail
    -0.69
     notch
    -0.69
    ordes
    -0.68
    plings
    -0.66
    ciating
    -0.65
    ¶
    -0.64
    POSITIVE LOGITS
     confused
    1.06
     bothered
    1.06
     fooled
    1.02
     mistaken
    0.98
     intimidated
    0.97
     underestimated
    0.95
     ashamed
    0.95
     swayed
    0.92
     afraid
    0.91
     alarmed
    0.91
    Activations Density 0.100%

    No Known Activations