Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 19657
    Prev
    Next
    INDEX
    Explanations

    names or references to specific actors

    oai_token-act-pair · gpt-3.5-turbo

    the names of well-known actors and their significant roles in movies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Statistics
    -0.97
    oard
    -0.82
    Term
    -0.74
    Policy
    -0.68
    minimum
    -0.67
    Els
    -0.67
    æ³
    -0.67
    Fla
    -0.66
    STATE
    -0.65
    ntil
    -0.65
    POSITIVE LOGITS
     movies
    1.11
     audition
    1.11
    enegger
    1.10
     starring
    1.08
     films
    1.07
     actress
    1.07
     Actress
    1.06
     cameo
    1.05
     starred
    1.05
     actor
    1.05
    Activations Density 0.213%

    No Known Activations