© 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. 7578
    Prev
    Next
    INDEX
    Explanations

    the word "be" followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "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 @ 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
     Kamp
    -0.70
     Kurd
    -0.67
    Reply
    -0.66
     Album
    -0.63
     Blocks
    -0.62
     Ples
    -0.62
     Sr
    -0.62
    oleon
    -0.61
     hops
    -0.60
     accommodation
    -0.60
    POSITIVE LOGITS
    hemoth
    1.47
    heading
    1.41
    arers
    1.36
    fitting
    1.28
    ardless
    1.22
    acons
    1.21
    league
    1.18
    getting
    1.14
    ige
    1.14
    agle
    1.11
    Activations Density 0.055%

    No Known Activations