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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 17036
    Prev
    Next
    INDEX
    Explanations

    phrases related to people or events taking a physical stage

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "stage" and its contexts, particularly in performances or events

    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
    eco
    -0.69
    etheless
    -0.67
    alez
    -0.67
    imal
    -0.65
     Ide
    -0.64
    usterity
    -0.63
    ebook
    -0.62
    iHUD
    -0.62
    vironment
    -0.62
     Wonderland
    -0.61
    POSITIVE LOGITS
     podium
    1.14
     microphones
    1.02
     microphone
    0.95
    room
    0.93
     cheering
    0.92
     announcer
    0.91
     applause
    0.91
     speeches
    0.88
     laughter
    0.88
    rooms
    0.88
    Activations Density 0.143%

    No Known Activations