© 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. 11-RES-JB
    11. 7661
    Prev
    Next
    INDEX
    Explanations

    instances where something is being filled, such as gaps, roles, positions, voids, or orders

    oai_token-act-pair · gpt-3.5-turbo

    references to filling gaps or vacancies in various contexts

    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
    conduct
    -0.81
    hess
    -0.66
    hend
    -0.66
    esson
    -0.65
    Ń
    -0.65
     proceed
    -0.63
    saf
    -0.63
    aviour
    -0.62
     Married
    -0.62
     Conduct
    -0.62
    POSITIVE LOGITS
     gaps
    1.54
     void
    1.43
     gap
    1.38
     coffers
    1.34
     vacancies
    1.30
     vacancy
    1.30
     holes
    1.22
     hole
    1.20
     vacuum
    1.17
     slots
    1.16
    Activations Density 0.132%

    No Known Activations