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. 6-RES-JB
    6. 18116
    Prev
    Next
    INDEX
    Explanations

    phrases related to political events and figures

    oai_token-act-pair · gpt-3.5-turbo

    sentences or phrases that conclude with punctuation marks, indicating the end of statements or thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     endeavour
    -0.87
     enqu
    -0.82
     colours
    -0.77
     practise
    -0.74
     regeneration
    -0.73
     regenerate
    -0.73
     accelerator
    -0.72
     travellers
    -0.70
     measurement
    -0.70
     licence
    -0.70
    POSITIVE LOGITS
    Republicans
    1.20
    President
    1.19
    Republican
    1.16
    Asked
    1.13
    Washington
    1.12
    PHOTOS
    1.11
    WASHINGTON
    1.11
    Trump
    1.10
    Polit
    1.09
    CNN
    1.08
    Activations Density 0.670%

    No Known Activations