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

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 3869
    Prev
    Next
    INDEX
    Explanations

    phrases related to arguments or debates

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to various arguments or claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eco
    -0.73
     stocking
    -0.70
    ummer
    -0.68
    oho
    -0.68
     bom
    -0.68
     livest
    -0.67
    cler
    -0.67
    isner
    -0.66
    appy
    -0.66
    cy
    -0.66
    POSITIVE LOGITS
     arguments
    1.17
     argument
    1.08
    uments
    0.94
    argument
    0.90
    ative
    0.87
    ãĤ¦ãĤ¹
    0.87
    edIn
    0.84
     arguing
    0.83
    ļéĨĴ
    0.83
     Argument
    0.82
    Activations Density 0.018%

    No Known Activations