© 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. 0-RES-JB
    11. 16413
    Prev
    Next
    INDEX
    Explanations

    words related to "rising" or being "reborn."

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itton
    -0.67
     disable
    -0.66
    body
    -0.65
    mun
    -0.64
     delete
    -0.63
     humor
    -0.62
     proc
    -0.61
     purpose
    -0.61
    purpose
    -0.60
     license
    -0.59
    POSITIVE LOGITS
     Rising
    4.25
    rising
    1.83
     Falling
    1.45
     Reborn
    1.44
     rising
    1.33
     Rise
    1.31
     Emerging
    1.13
     Unleashed
    1.04
     Rebellion
    1.01
     Shattered
    1.01
    Activations Density 0.010%

    No Known Activations