Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 23522
    Prev
    Next
    INDEX
    Explanations

    words related to the usage or application of something in various contexts, such as medicine, law enforcement, or cooking

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the use of substances in various contexts

    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
    anse
    -0.73
    abe
    -0.70
    govtrack
    -0.70
    irl
    -0.70
    ibl
    -0.69
    ontent
    -0.69
    ovich
    -0.67
    iable
    -0.67
    ents
    -0.66
    hai
    -0.66
    POSITIVE LOGITS
     conjunction
    1.71
     lieu
    1.46
     tandem
    1.25
     constructing
    1.03
     combination
    1.03
     crafting
    1.01
     designing
    0.98
     contexts
    0.97
     emergencies
    0.97
     vain
    0.94
    Activations Density 0.176%

    No Known Activations