© 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. 9947
    Prev
    Next
    INDEX
    Explanations

    instances of the word "expatriate" or its variations in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "exp" within words

    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
     thumbs
    -0.66
    STEM
    -0.66
     Crom
    -0.66
    WORK
    -0.65
    enegger
    -0.64
    bugs
    -0.64
    footed
    -0.63
     Carnival
    -0.62
     Reconstruction
    -0.62
     Hipp
    -0.62
    POSITIVE LOGITS
    ropri
    1.37
    orters
    1.37
    anse
    1.26
    orter
    1.24
    ulsion
    1.22
    onents
    1.20
    uls
    1.14
    iring
    1.11
    ository
    1.10
    atri
    1.06
    Activations Density 0.040%

    No Known Activations