© 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. 12113
    Prev
    Next
    INDEX
    Explanations

    phrases related to making changes, strategies, and improvements in various systems or policies

    oai_token-act-pair · gpt-3.5-turbo
    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
     laughs
    -0.71
    enegger
    -0.67
    erity
    -0.64
    positive
    -0.64
    uine
    -0.63
    cellent
    -0.62
    eln
    -0.61
    putable
    -0.61
    eday
    -0.61
    ERROR
    -0.60
    POSITIVE LOGITS
     workflow
    1.17
     structure
    1.15
     rosters
    1.12
     procedures
    1.10
     policies
    1.06
     schedules
    1.05
     posture
    1.04
     protocols
    1.03
     practices
    1.02
     layouts
    1.01
    Activations Density 0.428%

    No Known Activations