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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7590
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and activities

    oai_token-act-pair · gpt-3.5-turbo

    discussions related to political actions and events

    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
     tyre
    -0.94
     tyres
    -0.90
    celona
    -0.87
    teness
    -0.80
     Notting
    -0.79
     catalogue
    -0.78
     fuelled
    -0.78
    Buyable
    -0.76
    borgh
    -0.74
     recognise
    -0.74
    POSITIVE LOGITS
     Senators
    2.07
     senators
    2.07
     Senate
    1.98
    Senate
    1.91
     Senator
    1.72
     McConnell
    1.69
    Senator
    1.67
    Sen
    1.64
     Congressional
    1.63
     Schumer
    1.63
    Activations Density 0.550%

    No Known Activations