© 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. 1-RES-JB
    11. 428
    Prev
    Next
    INDEX
    Explanations

    comparisons using the word "like"

    oai_token-act-pair · gpt-3.5-turbo

    references to comparisons or analogies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inoa
    -0.83
    Dispatch
    -0.71
    ICH
    -0.70
    ysical
    -0.69
    inas
    -0.66
    duction
    -0.66
    Ö¼
    -0.65
    gencies
    -0.65
    elli
    -0.65
    achus
    -0.65
    POSITIVE LOGITS
    lihood
    2.06
    etheless
    1.29
    like
    1.17
    liness
    1.06
    minded
    1.04
    lier
    0.97
    terday
    0.96
    liest
    0.93
     minded
    0.88
    theless
    0.79
    Activations Density 0.012%

    No Known Activations