© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 21364
    Prev
    Next
    INDEX
    Explanations

    political terms and news-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    key figures and organizations in political discussions

    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
     licence
    -0.88
     licences
    -0.87
     practise
    -0.77
     recognise
    -0.76
     colours
    -0.75
    å
    -0.74
     realise
    -0.74
     civilisation
    -0.73
     recognised
    -0.73
     flavours
    -0.73
    POSITIVE LOGITS
     Politico
    1.41
     POLITICO
    1.40
    CNN
    1.19
     MSNBC
    1.16
    GOP
    1.10
     CNN
    1.09
     RNC
    1.07
    Politics
    1.07
     Hannity
    1.07
     Priebus
    1.06
    Activations Density 0.881%

    No Known Activations