© 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. 10-RES-JB
    11. 12749
    Prev
    Next
    INDEX
    Explanations

    phrases related to strategy games

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to gameplay mechanics and character development in gaming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    audi
    -0.68
    inventoryQuantity
    -0.65
    osure
    -0.65
    ixties
    -0.62
     understatement
    -0.61
    quickShipAvailable
    -0.61
    BuyableInstoreAndOnline
    -0.60
    sorry
    -0.60
    erva
    -0.59
     Borders
    -0.59
    POSITIVE LOGITS
     respective
    1.15
     predetermined
    1.14
     corresponding
    1.12
     desired
    0.95
     various
    0.93
     varying
    0.91
     whichever
    0.90
     specific
    0.89
     specified
    0.82
     randomly
    0.82
    Activations Density 0.590%

    No Known Activations