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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 0-RES-JB
    6. 11165
    Prev
    Next
    INDEX
    Explanations

    references to a gaming platform or software feature related to playing or controlling gameplay

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "play" in different contexts

    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
     rh
    -0.68
     latt
    -0.67
     Dag
    -0.67
     meth
    -0.66
     pal
    -0.64
     sticky
    -0.63
     ent
    -0.63
     DNA
    -0.62
     sig
    -0.61
     Constantine
    -0.61
    POSITIVE LOGITS
    Play
    3.84
    play
    1.88
    PLAY
    1.84
    plays
    1.56
    Playing
    1.55
     Play
    1.50
     Played
    1.50
    Players
    1.43
    played
    1.43
     PLAY
    1.43
    Activations Density 0.014%

    No Known Activations