© 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. 9-RES-JB
    11. 13584
    Prev
    Next
    INDEX
    Explanations

    words related to flags and national symbols

    oai_token-act-pair · gpt-3.5-turbo

    references to flags, particularly national and symbolic flags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irlf
    -0.70
    ugal
    -0.70
     contribut
    -0.69
    productive
    -0.69
    aky
    -0.67
    ĨĴ
    -0.65
    sth
    -0.65
     CK
    -0.65
    Parameter
    -0.65
     Ports
    -0.64
    POSITIVE LOGITS
     adorned
    1.26
     salute
    1.25
     mascot
    1.23
     tattoo
    1.22
     emoji
    1.16
     logo
    1.16
     etched
    1.14
     symbol
    1.12
     engraved
    1.09
     emblem
    1.08
    Activations Density 0.278%

    No Known Activations