© 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. 10-RES-JB
    11. 8229
    Prev
    Next
    INDEX
    Explanations

    economic and political terms related to government policies

    oai_token-act-pair · gpt-3.5-turbo

    references to political schemes and statements about economics

    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
    colored
    -1.11
    ADVERTISEMENT
    -1.11
     \"
    -0.94
    �
    -0.87
    ukemia
    -0.86
    defense
    -0.85
     utilizing
    -0.85
    Additionally
    -0.83
     utilized
    -0.83
    .","
    -0.82
    POSITIVE LOGITS
     Ukip
    1.55
     realise
    1.48
     recognise
    1.45
     Nato
    1.43
     scept
    1.41
     UKIP
    1.39
     organising
    1.36
     emphas
    1.36
     civilisation
    1.35
     organise
    1.35
    Activations Density 1.197%

    No Known Activations