© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6009
    Prev
    Next
    INDEX
    Explanations

    mentions of specific nationalities or groups of people

    oai_token-act-pair · gpt-3.5-turbo

    references to specific nationalities, particularly Germans and Russians, in historical contexts

    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
    tains
    -0.79
    antha
    -0.70
    ľ
    -0.68
    ¿½
    -0.68
    levels
    -0.67
    vironments
    -0.67
    states
    -0.66
    cells
    -0.65
    uces
    -0.62
    heid
    -0.62
    POSITIVE LOGITS
    '
    1.24
     themselves
    1.21
    ']
    1.05
    layer
    0.96
     intend
    0.94
    cale
    0.91
     are
    0.90
    hift
    0.90
     weren
    0.89
     were
    0.89
    Activations Density 0.167%

    No Known Activations