© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2815
    Prev
    Next
    INDEX
    Explanations

    variations or differences between multiple entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "different" 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
     ®
    -0.64
    ity
    -0.62
     lest
    -0.60
    advertising
    -0.60
    inth
    -0.60
    ulf
    -0.60
    ware
    -0.59
    edition
    -0.58
    bye
    -0.58
    hes
    -0.57
    POSITIVE LOGITS
     different
    3.37
    different
    2.70
     Different
    2.24
     differently
    2.19
     differing
    2.19
    Different
    2.08
     varying
    1.81
     differ
    1.71
     disparate
    1.65
     distinct
    1.64
    Activations Density 0.033%

    No Known Activations