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. 1-RES-JB
    6. 15318
    Prev
    Next
    INDEX
    Explanations

    words related to communication, such as "communication", "commitment", and "committee"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "committee" or "commission"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Walker
    -0.68
     Balk
    -0.68
    rers
    -0.67
     Ukrainian
    -0.66
    lings
    -0.66
     Asian
    -0.64
     Tribe
    -0.63
    wered
    -0.63
    taker
    -0.63
    uca
    -0.62
    POSITIVE LOGITS
     comm
    1.07
    puter
    1.02
    nesota
    0.95
    itted
    0.92
    uted
    0.91
     newcom
    0.91
    otion
    0.90
    essage
    0.88
    mercial
    0.86
    rontal
    0.83
    Activations Density 0.005%

    No Known Activations