© 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. 0-RES-JB
    11. 22262
    Prev
    Next
    INDEX
    Explanations

    phrases related to being on board or on stage

    oai_token-act-pair · gpt-3.5-turbo

    references to being in a particular location or situation related to performances or events

    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
    gem
    -0.73
     Poverty
    -0.67
    Cro
    -0.65
    iddles
    -0.65
    robe
    -0.62
    rose
    -0.62
    stat
    -0.61
    cum
    -0.60
    yg
    -0.60
     poverty
    -0.59
    POSITIVE LOGITS
     onboard
    4.01
     aboard
    2.26
     overboard
    1.55
     ashore
    1.34
     onstage
    1.28
     backstage
    1.19
     disembark
    1.07
     cockpit
    1.02
     passengers
    1.00
    boarding
    0.98
    Activations Density 0.018%

    No Known Activations