© 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. 7695
    Prev
    Next
    INDEX
    Explanations

    dates and specific numerical values related to events or quantities

    oai_token-act-pair · gpt-3.5-turbo

    instances of reported speech or statements made by individuals

    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
     tremend
    -0.99
     princ
    -0.88
     âĢķ
    -0.84
     utilizing
    -0.81
    ––
    -0.79
     carbohyd
    -0.79
    ñ
    -0.78
     bc
    -0.77
     eleph
    -0.74
    ¥ŀ
    -0.72
    POSITIVE LOGITS
    Image
    1.62
    Analysis
    1.48
    Media
    1.45
    BBC
    1.37
    Mr
    1.26
    Ms
    1.17
    Mrs
    1.14
    Prof
    1.06
    Thousands
    1.03
    About
    1.02
    Activations Density 0.119%

    No Known Activations