© 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. 11475
    Prev
    Next
    INDEX
    Explanations

    names of individuals, specifically focusing on the name "Ralph" with varying intensities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individual names

    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
    glers
    -0.96
    mble
    -0.74
    tenance
    -0.73
    ly
    -0.73
    ppelin
    -0.73
    Asia
    -0.69
    flies
    -0.68
    ning
    -0.67
    kers
    -0.66
    lder
    -0.66
    POSITIVE LOGITS
    onse
    0.98
     Lauren
    0.97
     Wald
    0.95
    osal
    0.86
    onso
    0.85
     Miliband
    0.84
    abet
    0.83
    inating
    0.78
    ie
    0.78
    ides
    0.74
    Activations Density 0.041%

    No Known Activations