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. 6157
    Prev
    Next
    INDEX
    Explanations

    words related to positive attributes or qualities like grace and elegance

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "grace" in various contexts

    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
    RAW
    -0.75
    ALK
    -0.72
    WD
    -0.69
    ONE
    -0.68
     liter
    -0.60
     asthma
    -0.60
     Turks
    -0.60
     proprietary
    -0.59
     Oral
    -0.58
     seq
    -0.57
    POSITIVE LOGITS
    fully
    1.15
     grace
    1.08
    fulness
    1.01
    aciously
    0.91
    byss
    0.91
    ibility
    0.90
    ously
    0.89
    lication
    0.88
    ably
    0.86
    ful
    0.86
    Activations Density 0.005%

    No Known Activations