© 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. 15489
    Prev
    Next
    INDEX
    Explanations

    proper nouns starting with the letter "P" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character "P" followed by a number or designation

    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
     Rebels
    -0.82
     diplom
    -0.73
     extraction
    -0.62
     adm
    -0.62
     vested
    -0.62
     descending
    -0.61
     ancest
    -0.61
     juggling
    -0.60
     Breaking
    -0.59
     centrif
    -0.59
    POSITIVE LOGITS
    ainted
    1.29
    ivot
    1.29
    aired
    1.25
    ardon
    1.24
    erenn
    1.24
    uebl
    1.21
    ussy
    1.19
    oultry
    1.19
    regnancy
    1.19
    ierce
    1.17
    Activations Density 0.038%

    No Known Activations