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. 3-RES-JB
    6. 19656
    Prev
    Next
    INDEX
    Explanations

    words related to organized plans or systems

    oai_token-act-pair · gpt-3.5-turbo

    the term "scheme" in various contexts and meanings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rated
    -0.63
    Nob
    -0.62
    minent
    -0.60
     runaway
    -0.57
     fir
    -0.56
    Posts
    -0.56
    ulu
    -0.56
    thening
    -0.55
    raised
    -0.55
    uckland
    -0.55
    POSITIVE LOGITS
     schemes
    1.07
     scheme
    1.05
    urally
    0.86
    etting
    0.83
     Scheme
    0.78
    matically
    0.77
    ologies
    0.77
    etter
    0.76
    eering
    0.75
     lawy
    0.74
    Activations Density 0.008%

    No Known Activations