© 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 EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 18844
    Prev
    Next
    INDEX
    Explanations

    common questions or phrases often asked or used in responses

    oai_token-act-pair · gpt-3.5-turbo

    questions and phrases related to common inquiries or misunderstandings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     totality
    -0.72
    hod
    -0.69
     Pict
    -0.65
    Delivery
    -0.64
    istrate
    -0.63
    etermined
    -0.61
    rity
    -0.60
    66666666
    -0.60
    xton
    -0.60
    hest
    -0.59
    POSITIVE LOGITS
     debates
    1.00
     critiques
    0.90
     misconceptions
    0.89
     nowadays
    0.89
     discussions
    0.88
     whenever
    0.86
     discussing
    0.86
     conversations
    0.84
     lately
    0.84
     errone
    0.84
    Activations Density 0.377%

    No Known Activations