© 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. 0-RES-JB
    11. 1378
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific name, "Kit Nielsen"

    oai_token-act-pair · gpt-3.5-turbo

    specific names and terms related to individuals and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utor
    -0.78
    xual
    -0.77
     Croatian
    -0.73
    translation
    -0.73
    vez
    -0.72
     Rhodes
    -0.71
    DCS
    -0.70
    Ven
    -0.68
    activate
    -0.66
    azer
    -0.66
    POSITIVE LOGITS
     Annie
    1.70
     Dow
    1.50
     Rupert
    1.47
     Nielsen
    1.43
    Kit
    1.34
     Berkshire
    1.17
     Bert
    1.16
    Ni
    1.15
     Frances
    1.13
     Mick
    1.13
    Activations Density 0.061%

    No Known Activations