© 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. 391
    Prev
    Next
    INDEX
    Explanations

    comparisons using the word "like"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "like."

    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
    aptic
    -0.75
    ells
    -0.69
    ulic
    -0.69
    icter
    -0.68
    Ire
    -0.68
    ittal
    -0.66
    division
    -0.66
    Limited
    -0.65
    UCT
    -0.65
    illance
    -0.63
    POSITIVE LOGITS
    lihood
    1.77
    liest
    1.24
    lier
    1.16
     many
    1.00
    liness
    0.99
    ly
    0.91
     clock
    0.89
     any
    0.86
     most
    0.85
     countless
    0.85
    Activations Density 0.049%

    No Known Activations