© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 6989
    Prev
    Next
    INDEX
    Explanations

    dates and proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    presence of financial and healthcare-related terms or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whilst
    -1.03
     humour
    -1.03
     util
    -1.02
     horrend
    -0.97
     eleph
    -0.97
     enqu
    -0.96
     civilisation
    -0.92
     endeavour
    -0.91
     analys
    -0.90
     colours
    -0.90
    POSITIVE LOGITS
    Newsletter
    2.01
    Officials
    1.73
    Neither
    1.69
    Among
    1.68
    Asked
    1.68
    Critics
    1.67
    ___
    1.65
    Several
    1.62
    Still
    1.61
    Advertisement
    1.60
    Activations Density 0.407%

    No Known Activations