© 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. 0-RES-JB
    11. 8365
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the movie "Forrest Gump"

    oai_token-act-pair · gpt-3.5-turbo

    references to the character Forrest Gump

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Orb
    -1.03
     Pod
    -0.87
    Pod
    -0.82
    ova
    -0.77
    EU
    -0.77
     Phant
    -0.77
    Unity
    -0.73
     Kiev
    -0.73
     Mold
    -0.73
     EU
    -0.72
    POSITIVE LOGITS
     Forrest
    2.95
     Rocky
    1.31
     Oprah
    1.19
     Twain
    1.07
     motivational
    1.06
     abolition
    1.00
     Frazier
    1.00
     Elvis
    1.00
     Clint
    0.97
     Lone
    0.97
    Activations Density 0.080%

    No Known Activations