© 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. 22102
    Prev
    Next
    INDEX
    Explanations

    researchers and authors involved in studies or experiments

    oai_token-act-pair · gpt-3.5-turbo

    references to researchers and authors involved in scientific studies

    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
     srfAttach
    -0.83
    CLASSIFIED
    -0.68
     dues
    -0.66
     Friend
    -0.65
    ãĥĸ
    -0.65
     Allies
    -0.65
    VW
    -0.64
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.64
     actionGroup
    -0.64
    Friend
    -0.64
    POSITIVE LOGITS
     conclude
    1.20
     speculate
    1.17
     analyzed
    1.16
     hypothesized
    1.12
     hypothes
    1.12
     analysed
    1.11
     suggest
    1.06
     concluded
    1.04
     propose
    1.04
     examined
    1.03
    Activations Density 0.071%

    No Known Activations