© 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. 10-RES-JB
    11. 6459
    Prev
    Next
    INDEX
    Explanations

    past tense verbs, specifically "was."

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     subscrib
    -0.75
    ertodd
    -0.72
    depth
    -0.71
    abet
    -0.69
    imeter
    -0.68
    ples
    -0.68
    rc
    -0.68
    wich
    -0.67
    isode
    -0.66
    ennial
    -0.66
    POSITIVE LOGITS
     obvious
    0.93
     raining
    0.92
     unclear
    0.90
     easier
    0.89
     clear
    0.87
     evident
    0.85
     doubtful
    0.85
     impossible
    0.85
     possible
    0.81
     incumbent
    0.80
    Activations Density 0.167%

    No Known Activations