© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 18687
    Prev
    Next
    INDEX
    Explanations

    social media related terms like usernames and hashtags

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to blogs and online commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     civilisation
    -0.81
     licence
    -0.74
     mould
    -0.74
     colours
    -0.73
     realise
    -0.70
     realised
    -0.70
     recognise
    -0.68
     ageing
    -0.66
     metre
    -0.63
     endeavour
    -0.62
    POSITIVE LOGITS
     Politico
    1.10
    Republicans
    1.05
     Corker
    1.04
     Pelosi
    1.04
    partisan
    1.03
    Senator
    1.01
    Republican
    0.99
     POLITICO
    0.99
    Senate
    0.97
     Priebus
    0.97
    Activations Density 1.764%

    No Known Activations