© 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. 17723
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases containing the word 'and'

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases that indicate connections or relationships among ideas or subjects

    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
    ril
    -0.71
    payer
    -0.68
    usha
    -0.67
    BIL
    -0.64
    resh
    -0.63
    isive
    -0.63
    >[
    -0.63
    elia
    -0.63
    ocrat
    -0.63
    trak
    -0.62
    POSITIVE LOGITS
     elsewhere
    1.56
     beyond
    1.15
     across
    0.94
     abroad
    0.94
     throughout
    0.94
     anywhere
    0.93
     everywhere
    0.92
     thereafter
    0.88
     onto
    0.87
     onwards
    0.83
    Activations Density 0.423%

    No Known Activations