© 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
    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. 7205
    Prev
    Next
    INDEX
    Explanations

    quotations from BBC news reports

    oai_token-act-pair · gpt-3.5-turbo

    mentions of news programs and their sources or presenters

    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
     totaling
    -0.89
     feces
    -0.84
     utilizing
    -0.82
     victimized
    -0.79
     publicized
    -0.79
     Kappa
    -0.79
     utilized
    -0.78
     Craigslist
    -0.77
     tumor
    -0.77
     Yelp
    -0.77
    POSITIVE LOGITS
    BBC
    1.68
     BBC
    1.66
     programme
    1.41
     presenter
    1.27
     BST
    1.22
     programmes
    1.22
     ITV
    1.15
     Programme
    1.15
     Scotland
    1.14
     Britain
    1.13
    Activations Density 0.271%

    No Known Activations