© 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. 19498
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific "Saga"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "saga" in various contexts

    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
    gettable
    -0.85
    affer
    -0.81
    aturally
    -0.74
    itions
    -0.73
    Ĥ¬
    -0.71
    rouch
    -0.71
    kHz
    -0.71
    iculty
    -0.70
    owler
    -0.70
    anged
    -0.70
    POSITIVE LOGITS
     Saga
    1.04
     Reincarn
    0.81
    UAL
    0.81
    âĵĺ
    0.79
     è£ıè
    0.79
     saga
    0.78
     Tales
    0.77
     Reborn
    0.77
     Chronicles
    0.75
     sag
    0.74
    Activations Density 0.011%

    No Known Activations