© 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. 11835
    Prev
    Next
    INDEX
    Explanations

    comparisons or similarities between different entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "comparable" and its variations

    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
    ts
    -0.69
    estead
    -0.63
    hid
    -0.60
    eal
    -0.59
    soon
    -0.59
    Mail
    -0.59
    eds
    -0.58
    dir
    -0.58
    ke
    -0.57
    ella
    -0.57
    POSITIVE LOGITS
     comparable
    3.62
     similar
    2.00
     analogous
    1.97
     equivalent
    1.92
     compar
    1.92
    similar
    1.59
     similarly
    1.42
     equivalents
    1.31
     identical
    1.29
     equival
    1.29
    Activations Density 0.018%

    No Known Activations