© 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. 2-RES-JB
    11. 768
    Prev
    Next
    INDEX
    Explanations

    the past participle 'launched'

    oai_token-act-pair · gpt-4-turbo

    phrases related to initiating or starting something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "launched" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uth
    -0.68
    iane
    -0.68
    info
    -0.66
    cious
    -0.65
    nton
    -0.65
    iola
    -0.64
    andro
    -0.63
     Room
    -0.63
     Supervisor
    -0.61
    ection
    -0.61
    POSITIVE LOGITS
    laun
    1.02
     laun
    0.96
     launched
    0.94
     launching
    0.93
     catapult
    0.92
    EStream
    0.92
    launch
    0.91
     Seym
    0.89
    Laun
    0.88
    wcs
    0.88
    Activations Density 0.017%

    No Known Activations