Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 10614
    Prev
    Next
    INDEX
    Explanations

    phrases urging action

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "Let" followed by a directive or suggestion

    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
     unspecified
    -0.70
     affected
    -0.67
     dead
    -0.65
     invasive
    -0.65
     damaged
    -0.64
     active
    -0.63
     battery
    -0.63
     equivalent
    -0.63
     planned
    -0.62
     experienced
    -0.61
    POSITIVE LOGITS
    Let
    3.07
     Let
    2.19
     LET
    1.66
    Consider
    1.62
     Lets
    1.61
    LET
    1.59
    let
    1.51
    Here
    1.50
     let
    1.50
    Alright
    1.49
    Activations Density 0.009%

    No Known Activations