© 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. 4940
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases related to news headlines

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation and sentence endings

    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
     nodd
    -1.06
     quir
    -0.91
    yip
    -0.83
     notor
    -0.81
     dared
    -0.76
     unbeliev
    -0.76
     taboo
    -0.76
     unsus
    -0.76
     whiff
    -0.75
     paycheck
    -0.74
    POSITIVE LOGITS
     Accordingly
    1.39
     Our
    1.35
     We
    1.33
     Additionally
    1.28
     Furthermore
    1.27
     Therefore
    1.24
     However
    1.21
     Consequently
    1.19
     Unfortunately
    1.18
    âĢİ
    1.18
    Activations Density 0.211%

    No Known Activations