© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 17274
    Prev
    Next
    INDEX
    Explanations

    phrases related to quantifying a reduced amount or number of something

    oai_token-act-pair · gpt-3.5-turbo

    instances where the concept of having fewer of something is discussed

    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
    wrapper
    -0.72
    afort
    -0.70
    notation
    -0.68
    fan
    -0.65
    andise
    -0.65
    phrase
    -0.65
     Everywhere
    -0.64
    Loading
    -0.64
    DNA
    -0.64
     tremend
    -0.64
    POSITIVE LOGITS
     calories
    1.04
     opportunities
    1.00
     than
    1.00
     distractions
    0.98
     entries
    0.95
     occurrences
    0.94
     servings
    0.93
     copies
    0.93
     hours
    0.91
     instances
    0.88
    Activations Density 0.065%

    No Known Activations