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. 1-RES-JB
    6. 4507
    Prev
    Next
    INDEX
    Explanations

    phrases related to preparation or readiness

    oai_token-act-pair · gpt-3.5-turbo

    references to preparation, particularly in a context related to cooking or planning activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Butterfly
    -0.82
    dylib
    -0.67
    */(
    -0.67
    geist
    -0.65
     Roses
    -0.64
     Bri
    -0.60
     Roe
    -0.59
     Lotus
    -0.58
     Whis
    -0.58
     Millennium
    -0.58
    POSITIVE LOGITS
     prep
    1.16
    prep
    1.12
    oster
    1.07
    alach
    0.93
    ublic
    0.92
    Prep
    0.91
    otent
    0.90
    regnancy
    0.88
    ovember
    0.86
    agin
    0.86
    Activations Density 0.004%

    No Known Activations