© 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. 22635
    Prev
    Next
    INDEX
    Explanations

    words related to business and entrepreneurship

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to entrepreneurship and common mistakes in business

    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
    arbon
    -0.76
    packages
    -0.75
    ropolitan
    -0.74
    ufact
    -0.73
    Lago
    -0.73
    cape
    -0.72
    stantial
    -0.72
     renovations
    -0.70
    ographs
    -0.70
    estial
    -0.69
    POSITIVE LOGITS
     fallacy
    1.59
     misconception
    1.30
     pitfalls
    1.24
     trope
    1.18
     Syndrome
    1.16
     misunderstanding
    1.15
     syndrome
    1.13
     misconceptions
    1.12
     dilemma
    1.11
     dreaded
    1.10
    Activations Density 0.552%

    No Known Activations