© 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. 10-RES-JB
    11. 13574
    Prev
    Next
    INDEX
    Explanations

    quotations in text

    oai_token-act-pair · gpt-3.5-turbo

    punctuations and phrases related to presidential statements and public opinion

    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
     sorce
    -0.82
    tube
    -0.81
     pulp
    -0.78
    Monster
    -0.77
     sorcery
    -0.77
    apesh
    -0.77
    mol
    -0.75
     psychiat
    -0.74
    xual
    -0.72
     lic
    -0.72
    POSITIVE LOGITS
     Obama
    2.21
    Obama
    2.14
     Barack
    1.56
     Biden
    1.47
     President
    1.30
     Romney
    1.27
     McCain
    1.27
     Presidents
    1.18
     Boehner
    1.17
     presidents
    1.16
    Activations Density 0.363%

    No Known Activations