© 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. 7-RES-JB
    11. 1611
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly "Nate."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly focusing on the name "Nate."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iance
    -1.07
    loo
    -0.97
    iances
    -0.91
    ijk
    -0.86
    ily
    -0.82
    osite
    -0.79
    usc
    -0.77
    stadt
    -0.74
    ies
    -0.74
    aunder
    -0.74
    POSITIVE LOGITS
    IELD
    0.77
    heastern
    0.75
    hower
    0.71
    ãĤ¡
    0.69
    BLIC
    0.65
     Manson
    0.65
    eor
    0.64
    ÃįÃį
    0.64
    ppo
    0.63
     Niet
    0.62
    Activations Density 0.078%

    No Known Activations