© 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. 1985
    Prev
    Next
    INDEX
    Explanations

    terms related to starting, beginning, or initiating actions or processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the act of starting or beginning something

    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
     Gould
    -0.67
    aver
    -0.66
    enegger
    -0.65
    Chance
    -0.63
    âĢ¢âĢ¢
    -0.62
    avering
    -0.61
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.60
     warehouses
    -0.59
    Bey
    -0.58
     warehouse
    -0.58
    POSITIVE LOGITS
     initi
    1.05
     initiated
    0.91
    TAIN
    0.89
     initiation
    0.89
    rative
    0.89
    phase
    0.87
    uberty
    0.86
     initiate
    0.85
    chnology
    0.85
    uates
    0.84
    Activations Density 0.013%

    No Known Activations