© 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. 6-RES-JB
    11. 2959
    Prev
    Next
    INDEX
    Explanations

    terms related to opposition or contrasting viewpoints

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving 'back-and-forth' interactions or debates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulhu
    -0.77
    ãģ®éŃĶ
    -0.70
    ãĤ¼ãĤ¦ãĤ¹
    -0.69
     Phi
    -0.69
     DOI
    -0.69
     Volcano
    -0.69
     Parenthood
    -0.64
     improv
    -0.62
    iaz
    -0.61
     QC
    -0.61
    POSITIVE LOGITS
    end
    1.14
    backed
    1.06
    eyed
    1.04
    to
    1.02
    side
    1.01
    arching
    1.00
    based
    0.99
    office
    0.98
    eye
    0.97
    front
    0.97
    Activations Density 0.081%

    No Known Activations