© 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. 12494
    Prev
    Next
    INDEX
    Explanations

    past tense verbs preceded by "if"

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements involving the word "were" and its variations

    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
    abre
    -0.68
     +++
    -0.68
    oria
    -0.67
    Products
    -0.66
    NOTE
    -0.61
    âĿ
    -0.61
     Reports
    -0.57
     Decay
    -0.57
     Quarterly
    -0.57
    mania
    -0.57
    POSITIVE LOGITS
     hypot
    0.83
    wolves
    0.80
    nt
    0.74
     truly
    0.74
     ever
    0.73
     somehow
    0.73
     genuinely
    0.69
    webkit
    0.66
     EVER
    0.65
     solely
    0.63
    Activations Density 0.075%

    No Known Activations