© 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. 1-RES-JB
    11. 3721
    Prev
    Next
    INDEX
    Explanations

    references to performances or roles in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "played."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ortium
    -0.80
    icon
    -0.69
    ciples
    -0.68
    heric
    -0.68
    por
    -0.68
    ordinate
    -0.68
    hak
    -0.67
    attribute
    -0.66
    plet
    -0.65
    owder
    -0.65
    POSITIVE LOGITS
     played
    1.10
     Playing
    0.99
     Played
    0.99
    wright
    0.96
     Plays
    0.95
    plays
    0.93
     playing
    0.84
    Play
    0.84
     Piano
    0.84
     Solitaire
    0.82
    Activations Density 0.020%

    No Known Activations