© 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. 10-RES-JB
    11. 20563
    Prev
    Next
    INDEX
    Explanations

    phrases that compare and contrast positive and negative aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases indicating a contrast between positive and negative aspects

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vernment
    -0.82
    sbm
    -0.78
    ICLE
    -0.75
    20439
    -0.74
    quit
    -0.69
     Intake
    -0.69
    ebin
    -0.67
    ciating
    -0.67
    sections
    -0.66
    igraph
    -0.66
    POSITIVE LOGITS
     evil
    1.01
     brightest
    0.99
    evil
    0.99
     cheerful
    0.96
     shiny
    0.96
     noble
    0.96
     honorable
    0.94
     fluffy
    0.94
     virtuous
    0.91
     tidy
    0.91
    Activations Density 0.110%

    No Known Activations