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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 3628
    Prev
    Next
    INDEX
    Explanations

    adjectives and nouns related to specificity or particularity

    oai_token-act-pair · gpt-3.5-turbo

    references to specific characteristics or conditions related to objects, concepts, and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ernels
    -1.13
    hops
    -0.97
    ptions
    -0.94
    tests
    -0.90
    enaries
    -0.89
    ometers
    -0.89
    ributes
    -0.88
    stories
    -0.87
    packages
    -0.86
    nces
    -0.86
    POSITIVE LOGITS
     piece
    1.28
     person
    1.23
     item
    1.22
     situation
    1.12
     entity
    1.12
     opponent
    1.10
     object
    1.09
     event
    1.09
     organism
    1.06
     creature
    1.06
    Activations Density 0.327%

    No Known Activations