© 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. 11-RES-JB
    11. 9520
    Prev
    Next
    INDEX
    Explanations

    phrases indicating assumptions or expectations

    oai_token-act-pair · gpt-3.5-turbo

    expressions of hypothetical situations or conjectures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Countdown
    -0.61
    rawdownloadcloneembedreportprint
    -0.58
     Tonight
    -0.57
    Enough
    -0.56
     Leilan
    -0.55
     lobb
    -0.54
     Canberra
    -0.54
     Brill
    -0.54
     Gutenberg
    -0.54
    Ready
    -0.53
    POSITIVE LOGITS
     expect
    1.31
     think
    1.23
     imagine
    1.14
     guess
    1.05
     assume
    1.04
     suppose
    1.04
     presume
    1.04
     wonder
    1.00
     hope
    0.97
     suspect
    0.96
    Activations Density 0.077%

    No Known Activations