© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 9838
    Prev
    Next
    INDEX
    Explanations

    terms related to resources, such as energy efficiency, resource collection, and resource management

    oai_token-act-pair · gpt-3.5-turbo

    references to resources and their management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arella
    -0.87
    lihood
    -0.73
    ker
    -0.73
    alone
    -0.71
     Mock
    -0.70
    erella
    -0.69
    £ı
    -0.68
    ŃĶ
    -0.68
    deals
    -0.68
    azeera
    -0.67
    POSITIVE LOGITS
    fulness
    1.09
     resources
    0.95
     allocation
    0.95
    ful
    0.84
     utilization
    0.84
     allocations
    0.83
    ourcing
    0.78
    iture
    0.78
     management
    0.77
     expended
    0.76
    Activations Density 0.047%

    No Known Activations