© 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. 20507
    Prev
    Next
    INDEX
    Explanations

    text related to data analysis and comparison

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to data comparisons and rankings

    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
     srfAttach
    -0.76
     Donation
    -0.76
     VIDEOS
    -0.75
    VIDEO
    -0.74
     Talks
    -0.74
     Goodbye
    -0.73
    INGTON
    -0.72
    hello
    -0.68
     Amen
    -0.68
    Peace
    -0.68
    POSITIVE LOGITS
     calculate
    1.57
     subtract
    1.45
     estimate
    1.43
     extrap
    1.36
     compute
    1.33
     calculated
    1.32
     computed
    1.31
     disag
    1.29
     weighted
    1.28
     calculates
    1.27
    Activations Density 0.370%

    No Known Activations