© 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. 11-RES-JB
    11. 7101
    Prev
    Next
    INDEX
    Explanations

    words related to physical health and well-being

    oai_token-act-pair · gpt-3.5-turbo
    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
    PsyNetMessage
    -0.79
    itiveness
    -0.75
     Width
    -0.74
    width
    -0.72
    Width
    -0.72
    before
    -0.69
     Whites
    -0.68
     guid
    -0.67
    ooth
    -0.64
     srfAttach
    -0.62
    POSITIVE LOGITS
     virtual
    0.92
     artificial
    0.91
     synthetic
    0.89
     fictional
    0.87
     imagined
    0.82
     inferred
    0.78
     fiction
    0.75
    virtual
    0.75
     supernatural
    0.74
     digital
    0.73
    Activations Density 0.189%

    No Known Activations