© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 17444
    Prev
    Next
    INDEX
    Explanations

    references to the author Aldous Huxley

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the name "Aldous Huxley."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pmwiki
    -0.72
    plementation
    -0.60
     Nare
    -0.59
    stakes
    -0.57
     Patreon
    -0.56
     dism
    -0.56
     sight
    -0.56
    terday
    -0.55
    former
    -0.55
    essional
    -0.54
    POSITIVE LOGITS
    uin
    1.14
    rums
    1.03
    rich
    1.02
    erman
    1.01
    ridge
    0.97
    erg
    0.92
    win
    0.90
    sburg
    0.89
    wich
    0.88
    orf
    0.87
    Activations Density 0.024%

    No Known Activations