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. 13924
    Prev
    Next
    INDEX
    Explanations

    technical terms related to the concept of complexity

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of complexity in various contexts

    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
    nesium
    -0.75
    ibur
    -0.69
    rine
    -0.68
    amina
    -0.66
    ties
    -0.65
    va
    -0.65
    ved
    -0.64
     corpor
    -0.63
    entin
    -0.62
    inal
    -0.62
    POSITIVE LOGITS
     complexity
    0.84
    iness
    0.83
    lessness
    0.81
    afety
    0.80
    anship
    0.79
    externalActionCode
    0.77
     richness
    0.76
    jriwal
    0.75
    iest
    0.75
    bender
    0.74
    Activations Density 0.029%

    No Known Activations