© 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. 12371
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a comparison between two contrasting entities

    oai_token-act-pair · gpt-3.5-turbo

    references to contrasting ideas or sides in a discussion

    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
    ensibly
    -0.76
    agra
    -0.65
    terday
    -0.64
     absorbs
    -0.60
    izable
    -0.57
    ensis
    -0.57
     1915
    -0.56
    wed
    -0.54
    burg
    -0.54
     completes
    -0.54
    POSITIVE LOGITS
     side
    0.83
    axis
    0.79
     hemisphere
    0.78
    worldly
    0.75
     table
    0.74
    ĺħ
    0.70
     occasions
    0.70
     continent
    0.70
    ename
    0.70
     periphery
    0.69
    Activations Density 0.039%

    No Known Activations