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. 11-RES-JB
    6. 10409
    Prev
    Next
    INDEX
    Explanations

    positive adjectives describing creative works

    oai_token-act-pair · gpt-3.5-turbo

    descriptive phrases that convey enjoyment and quality in storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocobo
    -0.83
    ulia
    -0.81
    llor
    -0.77
     Preferred
    -0.76
    foundland
    -0.75
    igslist
    -0.75
    culosis
    -0.75
    assium
    -0.74
    isance
    -0.72
    omial
    -0.71
    POSITIVE LOGITS
     poignant
    1.41
     insightful
    1.37
     immersive
    1.35
     entertaining
    1.35
     thrilling
    1.34
     inventive
    1.34
     hilarious
    1.30
     humorous
    1.29
     gripping
    1.28
     witty
    1.27
    Activations Density 0.190%

    No Known Activations