© 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. 11-RES-JB
    11. 20560
    Prev
    Next
    INDEX
    Explanations

    second person pronouns followed by verbs

    oai_token-act-pair · gpt-3.5-turbo

    references to player involvement and agency in games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soType
    -1.00
    statement
    -0.81
    quickShipAvailable
    -0.78
    Correction
    -0.77
    Lago
    -0.76
    inventoryQuantity
    -0.74
     stigma
    -0.71
     spurious
    -0.70
     apologizing
    -0.69
    Acknowled
    -0.66
    POSITIVE LOGITS
     explore
    1.34
     traverse
    1.31
     unlock
    1.30
     infiltrate
    1.23
     customize
    1.22
     roam
    1.22
     undertake
    1.20
     interact
    1.19
     embark
    1.19
     wield
    1.17
    Activations Density 0.199%

    No Known Activations