© 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. 6-RES-JB
    11. 3606
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific term or brand (Op)

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "Op" which likely refers to a specific topic or concept in the document

    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
    åŃIJ
    -0.86
    ãĤ¼ãĤ¦ãĤ¹
    -0.82
    wagen
    -0.75
    ãĥ¯ãĥ³
    -0.73
     Hanson
    -0.73
    ILLE
    -0.72
    =~=~
    -0.72
    EngineDebug
    -0.70
     Faul
    -0.69
    hips
    -0.69
    POSITIVE LOGITS
    osite
    1.17
    yright
    1.03
    onent
    1.03
    aque
    1.02
    inion
    1.01
    iates
    0.99
    ressor
    0.95
    ression
    0.94
    rah
    0.94
    lique
    0.94
    Activations Density 0.021%

    No Known Activations