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. 14594
    Prev
    Next
    INDEX
    Explanations

    the word "essential" occurring in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "essential" or fundamental components

    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
    hare
    -0.76
    Roy
    -0.73
    ter
    -0.72
     Stall
    -0.71
    kers
    -0.69
     Hanson
    -0.68
    uddin
    -0.67
    adra
    -0.67
    OUT
    -0.67
    ften
    -0.66
    POSITIVE LOGITS
     essential
    0.95
     ingredient
    0.93
    essential
    0.90
     ingred
    0.89
     components
    0.86
     elements
    0.80
     essentials
    0.80
     element
    0.76
     prerequisite
    0.76
     organs
    0.74
    Activations Density 0.009%

    No Known Activations