© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 24458
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the beginning or starting point of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the word "the" and its various contexts of usage

    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
    ciples
    -0.75
    ortium
    -0.70
    reau
    -0.69
    tons
    -0.64
    ormal
    -0.63
    share
    -0.63
     respectively
    -0.63
    rupt
    -0.63
    gae
    -0.63
    addy
    -0.62
    POSITIVE LOGITS
     outset
    1.77
     standpoint
    1.48
     vantage
    1.35
     perspective
    1.28
     beginning
    1.22
     viewpoint
    1.20
     sidelines
    1.19
     moment
    1.18
     onset
    1.17
     start
    1.14
    Activations Density 0.096%

    No Known Activations