© 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. 16302
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to authority or decision-making

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating uncertainty or skepticism

    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
     Osw
    -0.85
    enegger
    -0.72
     Thomson
    -0.72
     Brist
    -0.69
     Yon
    -0.69
     airs
    -0.67
     Cyn
    -0.67
    ifications
    -0.67
     SN
    -0.66
     Tid
    -0.65
    POSITIVE LOGITS
    ¬
    1.65
    Ļ
    1.48
    ¡
    1.35
    ı
    1.32
    ĵ
    1.26
    ħ
    1.25
    ª
    1.24
    £
    1.24
    ¤
    1.23
    ĸ
    1.22
    Activations Density 0.381%

    No Known Activations