© 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. 7569
    Prev
    Next
    INDEX
    Explanations

    phrases related to giving full effort or attention

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the word "every" 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
    olas
    -0.89
    holders
    -0.75
    ees
    -0.69
    eers
    -0.68
    arters
    -0.66
    quished
    -0.65
    anwhile
    -0.65
    olves
    -0.65
    masters
    -0.65
     Metatron
    -0.64
    POSITIVE LOGITS
    THING
    1.48
     ounce
    1.40
     inch
    1.33
     conceivable
    1.31
     imaginable
    1.19
    thin
    1.13
     aspect
    1.13
     penny
    1.11
     facet
    1.05
    ones
    1.05
    Activations Density 0.049%

    No Known Activations