© 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. 0-RES-JB
    11. 14792
    Prev
    Next
    INDEX
    Explanations

    the word "exclusive" appearing in a text

    oai_token-act-pair · gpt-3.5-turbo

    the term "exclusive" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zh
    -0.88
    aleb
    -0.86
    brates
    -0.81
    yrs
    -0.71
    jar
    -0.71
    mong
    -0.68
    hammad
    -0.67
     Mn
    -0.66
    dies
    -0.65
    anooga
    -0.64
    POSITIVE LOGITS
     exclusive
    3.89
    exclusive
    3.08
     Exclusive
    2.76
     exclus
    2.18
     exclusively
    1.69
     unique
    1.18
    CLUS
    1.17
    clusive
    1.14
     proprietary
    1.06
     limited
    1.06
    Activations Density 0.010%

    No Known Activations