Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 17760
    Prev
    Next
    INDEX
    Explanations

    website URLs

    oai_token-act-pair · gpt-3.5-turbo

    references to online resources and technological upgrades

    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
    ÄŁ
    -1.24
    Mexico
    -0.89
    stanbul
    -0.86
    ı
    -0.85
     Mexican
    -0.84
     anarchist
    -0.84
    Mex
    -0.84
     Ankara
    -0.84
    idad
    -0.83
     taco
    -0.82
    POSITIVE LOGITS
     Microsoft
    1.84
     Windows
    1.84
    Microsoft
    1.81
     PowerShell
    1.76
    microsoft
    1.73
     Cortana
    1.70
    Windows
    1.69
     Redmond
    1.52
     Kinect
    1.41
     Lumia
    1.38
    Activations Density 0.261%

    No Known Activations