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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 4782
    Prev
    Next
    INDEX
    Explanations

    years or dates preceded by 'in'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "and" 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
    natureconservancy
    -0.91
    BIL
    -0.75
    Machine
    -0.73
    é¾įå
    -0.73
    º
    -0.73
    ellectual
    -0.72
    å¼
    -0.71
    Soc
    -0.69
    ä½
    -0.69
    NPR
    -0.68
    POSITIVE LOGITS
     again
    1.15
     thereafter
    1.12
     onwards
    1.12
     beyond
    1.11
     onward
    1.06
     2014
    0.92
     2012
    0.91
     early
    0.91
     2011
    0.90
     2010
    0.88
    Activations Density 0.103%

    No Known Activations