© 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. 2859
    Prev
    Next
    INDEX
    Explanations

    names of people, particularly those with last names commonly associated with color (e.g., White, Black, Green)

    oai_token-act-pair · gpt-3.5-turbo

    the last names of notable individuals

    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
     VIDE
    -0.68
     srfAttach
    -0.66
     polarization
    -0.62
     psi
    -0.61
     Haram
    -0.60
     Serie
    -0.59
     BOX
    -0.59
     Hydra
    -0.58
     Pastebin
    -0.58
     masked
    -0.58
    POSITIVE LOGITS
    stein
    1.36
    berger
    1.34
    croft
    1.34
    gren
    1.32
    cott
    1.32
    hill
    1.30
    worth
    1.29
    baum
    1.29
    field
    1.28
    burn
    1.27
    Activations Density 0.154%

    No Known Activations