© 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. 19296
    Prev
    Next
    INDEX
    Explanations

    words related to shifting, transferring, redirecting, or reallocation of resources and responsibilities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to financial or resource allocation changes

    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
    cone
    -0.76
    mpeg
    -0.72
    agate
    -0.72
    perfect
    -0.69
    comed
    -0.68
    Friend
    -0.67
    urat
    -0.67
    sie
    -0.67
    ilant
    -0.67
    ideshow
    -0.67
    POSITIVE LOGITS
     blame
    1.45
     responsibility
    1.37
     responsibilities
    1.37
     resources
    1.19
     burden
    1.14
     workload
    1.06
     funds
    1.06
     energies
    1.05
     focus
    1.04
     attention
    1.03
    Activations Density 0.249%

    No Known Activations