Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 15987
    Prev
    Next
    INDEX
    Explanations

    keywords related to the control and management of resources, such as terms related to production, conservation, supply, and distribution

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to resource management and control

    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
     bible
    -0.94
     cooker
    -0.93
     castle
    -0.90
     senate
    -0.90
     yacht
    -0.87
     castles
    -0.87
     pods
    -0.87
     yak
    -0.86
     maple
    -0.86
     tower
    -0.85
    POSITIVE LOGITS
     Affect
    1.60
     Recogn
    1.57
     Stress
    1.56
     Influence
    1.56
     Deter
    1.55
     Appropri
    1.55
     Loss
    1.54
     Diff
    1.52
     Failure
    1.51
     Exc
    1.51
    Activations Density 0.325%

    No Known Activations