© 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. 4-RES-JB
    11. 3734
    Prev
    Next
    INDEX
    Explanations

    references to the popular television series "Game of Thrones"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Game" and related phrases in the context of various games or events

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

    No Comments

    Negative Logits
    SourceFile
    -0.85
    abase
    -0.75
     trustworthy
    -0.75
    eret
    -0.67
    hirt
    -0.67
    catentry
    -0.65
    igham
    -0.64
    iband
    -0.64
    hyde
    -0.64
    ractive
    -0.63
    POSITIVE LOGITS
     guiActiveUnfocused
    0.81
    TAG
    0.78
    estyles
    0.74
     Thrones
    0.71
     Archdemon
    0.68
     Finder
    0.68
    shoot
    0.68
     toss
    0.67
     Rampage
    0.65
     forfeit
    0.64
    Activations Density 0.205%

    No Known Activations