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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11109
    Prev
    Next
    INDEX
    Explanations

    phrases related to evolution

    oai_token-act-pair · gpt-3.5-turbo

    the concept of evolution or development over time

    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
    any
    -0.66
    USD
    -0.65
    idding
    -0.63
    iso
    -0.63
    lement
    -0.62
    tein
    -0.62
    iss
    -0.62
    bery
    -0.61
    lb
    -0.60
     Ful
    -0.60
    POSITIVE LOGITS
     evolved
    3.52
     evolve
    2.23
     evolves
    2.06
     evolving
    1.93
     morphed
    1.91
     evolution
    1.74
     matured
    1.68
     mutated
    1.53
     evolutionary
    1.46
     Evolution
    1.43
    Activations Density 0.016%

    No Known Activations