© 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. 3-RES-JB
    11. 23189
    Prev
    Next
    INDEX
    Explanations

    words related to movie franchises or titles with the word 'Rises'

    oai_token-act-pair · gpt-3.5-turbo

    variations of the verb "to rise."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     }}
    -0.64
    ãĤ¼ãĤ¦ãĤ¹
    -0.62
     Webb
    -0.61
     âĸł
    -0.59
     mins
    -0.59
     explaining
    -0.57
     wa
    -0.57
    gypt
    -0.57
    aple
    -0.56
    ________________________
    -0.56
    POSITIVE LOGITS
    kefeller
    0.72
     Racer
    0.69
    lining
    0.65
    hester
    0.65
     Passenger
    0.62
    itialized
    0.62
     Riding
    0.61
    bard
    0.61
    restling
    0.61
    umatic
    0.61
    Activations Density 0.071%

    No Known Activations