© 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. 4-RES-JB
    11. 17055
    Prev
    Next
    INDEX
    Explanations

    references to comparisons with something/someone else

    oai_token-act-pair · gpt-3.5-turbo

    references to "other" entities or groups in comparison to a primary subject

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

    No Comments

    Negative Logits
    ffee
    -0.68
     1915
    -0.65
    assis
    -0.62
     Retrieved
    -0.62
    zai
    -0.62
    ony
    -0.61
     1962
    -0.60
     Bride
    -0.60
    >>>>>>>>
    -0.59
     ç¥ŀ
    -0.58
    POSITIVE LOGITS
    worldly
    1.80
     kinds
    1.02
     aspects
    0.97
     types
    0.92
     countries
    0.91
     peoples
    0.89
    wise
    0.88
     continents
    0.86
     senses
    0.85
     forms
    0.84
    Activations Density 0.097%

    No Known Activations