© 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. 22445
    Prev
    Next
    INDEX
    Explanations

    headlines or informative phrases that introduce important information

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating essential information or guidance

    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
    _{
    -0.76
     Discord
    -0.75
    ãĥŁ
    -0.72
     Saiyan
    -0.67
    ^{
    -0.66
    ¯
    -0.65
     fanbase
    -0.65
    76561
    -0.62
     ðŁĻĤ
    -0.62
    Ì
    -0.62
    POSITIVE LOGITS
     POLITICO
    1.20
    PHOTOS
    1.07
     TIME
    1.06
     HuffPost
    1.05
     slideshow
    1.05
     NPR
    1.03
     VICE
    1.01
    utterstock
    1.01
    CNN
    1.00
     CNN
    0.97
    Activations Density 0.276%

    No Known Activations