© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 1940
    Prev
    Next
    INDEX
    Explanations

    words related to software applications or services, particularly with the word "Play" in them

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "Play."

    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
    CTV
    -0.66
    RNA
    -0.65
     marg
    -0.65
    mort
    -0.65
     surn
    -0.64
    idium
    -0.62
    lycer
    -0.62
     constituents
    -0.60
    llah
    -0.60
    conv
    -0.60
    POSITIVE LOGITS
     Play
    3.74
    Play
    2.67
     Plays
    2.14
    play
    2.12
     play
    2.11
     PLAY
    2.08
     Playing
    1.76
     Played
    1.69
    PLAY
    1.61
     plays
    1.57
    Activations Density 0.011%

    No Known Activations