© 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. 6-RES-JB
    11. 17806
    Prev
    Next
    INDEX
    Explanations

    direct speech, quotations, and direct questions

    oai_token-act-pair · gpt-3.5-turbo

    dialogue and statements made by characters

    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
    £ı
    -0.85
    malink
    -0.69
    agos
    -0.65
    atures
    -0.62
    姫
    -0.61
     wildfires
    -0.61
    "]=>
    -0.61
    unity
    -0.61
    utton
    -0.60
    ãĥĩ
    -0.59
    POSITIVE LOGITS
     hello
    0.91
     aloud
    0.77
     politely
    0.76
     loudly
    0.74
    dayName
    0.71
    yip
    0.71
     goodbye
    0.71
     inviting
    0.68
     dissatisf
    0.67
     angrily
    0.66
    Activations Density 0.352%

    No Known Activations