© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 407
    Prev
    Next
    INDEX
    Explanations

    phrases related to sending or transmitting something

    oai_token-act-pair · gpt-3.5-turbo

    the act of sending or transmitting something

    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
    ibilities
    -0.72
    anu
    -0.71
    Occup
    -0.70
    itions
    -0.68
    exist
    -0.67
    pedia
    -0.66
    ancies
    -0.66
    abilities
    -0.63
    LC
    -0.62
    ifact
    -0.62
    POSITIVE LOGITS
     sending
    3.29
     Sending
    2.06
     send
    1.96
     sends
    1.80
     transmitting
    1.74
    send
    1.72
    Send
    1.64
     contacting
    1.62
     exchanging
    1.59
     submitting
    1.58
    Activations Density 0.013%

    No Known Activations