© 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. 10738
    Prev
    Next
    INDEX
    Explanations

    phrases or abbreviations related to different types of systems or programs

    oai_token-act-pair · gpt-3.5-turbo

    various types of parentheses and brackets, as well as phrases associated with definitions or meanings

    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
    udic
    -0.69
    vable
    -0.69
    ichick
    -0.68
    ettings
    -0.67
    rogens
    -0.67
     resume
    -0.62
    uv
    -0.61
    rodu
    -0.61
    braska
    -0.61
    vid
    -0.60
    POSITIVE LOGITS
    literally
    1.19
    meaning
    1.09
    sic
    0.85
     plural
    0.84
    translation
    0.83
     acron
    0.81
     pronounced
    0.80
    ãĤ¢ãĥ«
    0.78
     ãģ
    0.77
    ãģĹ
    0.77
    Activations Density 0.301%

    No Known Activations