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. 6-RES-JB
    6. 22271
    Prev
    Next
    INDEX
    Explanations

    phrases related to transactions or actions through a direct or indirect method

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various methods of communication or interaction, particularly in legal or organizational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ournal
    -0.84
    nai
    -0.73
    Beat
    -0.64
    verage
    -0.63
    utherford
    -0.63
    isu
    -0.62
     worshipped
    -0.61
    sburg
    -0.61
    hematically
    -0.58
    ERROR
    -0.58
    POSITIVE LOGITS
     intermediary
    1.00
     channels
    1.00
     prism
    0.94
     intermedi
    0.94
     lens
    0.87
     mediation
    0.84
     guise
    0.77
     conduit
    0.74
     courts
    0.71
     mechanisms
    0.71
    Activations Density 0.226%

    No Known Activations