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. 3-RES-JB
    6. 10200
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to politics

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name Theresa May and relevant dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ECTION
    -0.83
    ¥µ
    -0.79
    CHAPTER
    -0.77
    Depth
    -0.75
    Methods
    -0.75
     Hawai
    -0.75
     Fatal
    -0.73
    Miami
    -0.69
    ersion
    -0.68
    Strength
    -0.68
    POSITIVE LOGITS
     ministerial
    1.02
     scept
    0.89
     ally
    0.86
     pledged
    0.86
     appoint
    0.85
     allies
    0.83
     coalition
    0.83
     Brexit
    0.82
     ministers
    0.81
     reassured
    0.80
    Activations Density 0.060%

    No Known Activations