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. 0-RES-JB
    6. 5927
    Prev
    Next
    INDEX
    Explanations

    words related to simplifying or making things simpler

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "simplify" and its variations, indicating a focus on the concept of simplification

    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
    taboola
    -0.74
    mouth
    -0.72
    icipated
    -0.69
    ifer
    -0.67
     boycot
    -0.65
    arians
    -0.65
     Brock
    -0.64
     sway
    -0.63
     Ward
    -0.63
    ieth
    -0.63
    POSITIVE LOGITS
     simpl
    3.06
     simplify
    2.71
     simplified
    2.69
     simplicity
    2.57
     simpler
    2.35
     Simpl
    2.27
    simple
    1.81
     simplest
    1.73
    sim
    1.72
     simplistic
    1.68
    Activations Density 0.032%

    No Known Activations