© 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. 10-RES-JB
    11. 11553
    Prev
    Next
    INDEX
    Explanations

    phrases containing '&' followed by other words or terms

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the ampersand symbol (&)

    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
    atche
    -0.74
    SPONSORED
    -0.69
    adra
    -0.68
     misunder
    -0.65
     concentrating
    -0.64
    icycle
    -0.61
     supposed
    -0.61
     mattered
    -0.60
    senal
    -0.59
    ansas
    -0.59
    POSITIVE LOGITS
     Co
    0.97
     Friends
    0.97
     Sons
    0.86
     Associates
    0.84
     Company
    0.82
    GAN
    0.76
    optional
    0.75
     Partners
    0.75
    nect
    0.72
    galitarian
    0.69
    Activations Density 0.036%

    No Known Activations