© 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. 10-RES-JB
    11. 10335
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to comparisons using the phrase "Like"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "like" used in comparisons or examples

    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
    aptic
    -0.78
    hiba
    -0.73
    ells
    -0.69
    acht
    -0.66
    ulic
    -0.66
    icter
    -0.65
    bang
    -0.63
    ospel
    -0.62
    Independent
    -0.62
     enthusi
    -0.60
    POSITIVE LOGITS
    lihood
    1.79
    liest
    1.32
    lier
    1.18
     many
    1.07
     any
    0.97
    liness
    0.94
     countless
    0.89
    minded
    0.85
     everyone
    0.84
     clock
    0.84
    Activations Density 0.072%

    No Known Activations