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. 6702
    Prev
    Next
    INDEX
    Explanations

    phrases related to evolution or development

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of evolution or change over time

    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
    VP
    -0.78
    pled
    -0.69
    NP
    -0.68
    mir
    -0.66
    sol
    -0.66
    76561
    -0.65
    Ey
    -0.65
    holder
    -0.64
    olicited
    -0.64
    Assembly
    -0.64
    POSITIVE LOGITS
     evolve
    0.89
    anwhile
    0.80
     evolved
    0.77
    arily
    0.76
     evolving
    0.74
    ĸļ
    0.74
     evolves
    0.73
    iator
    0.73
    icter
    0.72
    ives
    0.72
    Activations Density 0.014%

    No Known Activations