© 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. 6-RES-JB
    11. 14518
    Prev
    Next
    INDEX
    Explanations

    names that start with "Abdul" and have varying activations depending on the specific name

    oai_token-act-pair · gpt-3.5-turbo

    specific names of Middle Eastern political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kefeller
    -0.90
     sugg
    -0.90
     arteries
    -0.72
     acad
    -0.71
    emouth
    -0.71
    flix
    -0.66
    eport
    -0.66
     gears
    -0.66
     moth
    -0.65
    chrom
    -0.65
    POSITIVE LOGITS
    ij士
    0.84
    Ń
    0.84
    ali
    0.82
    Kar
    0.78
    Rah
    0.78
     Amin
    0.77
    lah
    0.77
    irin
    0.76
    ÙĬ
    0.75
     Rahman
    0.74
    Activations Density 0.132%

    No Known Activations