© 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. 3-RES-JB
    11. 22826
    Prev
    Next
    INDEX
    Explanations

    mentions of **foreigners** in a document

    oai_token-act-pair · gpt-3.5-turbo

    references to foreigners

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Adams
    -0.67
    ucc
    -0.66
    Discussion
    -0.65
    Plex
    -0.65
    urations
    -0.65
    pton
    -0.64
    arah
    -0.63
    Progress
    -0.63
    abeth
    -0.63
    alist
    -0.63
    POSITIVE LOGITS
     abroad
    1.09
     overseas
    0.88
     foreigners
    0.86
    ophone
    0.84
     nationals
    0.84
     roaming
    0.78
     versa
    0.78
     undes
    0.76
    folk
    0.75
     whom
    0.74
    Activations Density 0.010%

    No Known Activations