© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 16803
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific phrase or brand name, namely "Legend of Korra"

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Legend of Korra" franchise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ted
    -0.72
    reon
    -0.67
    ting
    -0.67
    ters
    -0.67
    ffee
    -0.67
    ushes
    -0.66
    ushing
    -0.65
    artney
    -0.65
     midday
    -0.63
     station
    -0.63
    POSITIVE LOGITS
     Legend
    1.14
    Legend
    1.11
    uin
    0.88
    naire
    0.88
    Doc
    0.72
    Rank
    0.70
    Maker
    0.69
    erer
    0.67
     Tales
    0.66
     Contin
    0.66
    Activations Density 0.007%

    No Known Activations