© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 13006
    Prev
    Next
    INDEX
    Explanations

    pieces of text that are Op-Ed articles or opinion pieces

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "op-ed" and its variants in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¶ħ
    -0.79
     Galileo
    -0.75
    ILLE
    -0.72
    soever
    -0.71
    VILLE
    -0.70
     Suc
    -0.68
    åŃIJ
    -0.67
     Resurrection
    -0.67
    auga
    -0.66
    IRD
    -0.65
    POSITIVE LOGITS
     op
    1.03
    onent
    1.02
    orter
    0.96
    osite
    0.94
    iates
    0.93
    osta
    0.91
    inion
    0.90
    yright
    0.88
    aqu
    0.86
    ppy
    0.84
    Activations Density 0.005%

    No Known Activations