© 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. 2-RES-JB
    11. 23821
    Prev
    Next
    INDEX
    Explanations

    phrases related to political movements and controversial issues, particularly the BDS movement and antisemitism

    oai_token-act-pair · gpt-3.5-turbo

    references to the BDS movement and related themes of antisemitism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oise
    -0.77
    ously
    -0.67
    selves
    -0.66
    ufact
    -0.66
    nesota
    -0.64
    iping
    -0.64
    overs
    -0.63
    swick
    -0.62
    ths
    -0.62
    ciation
    -0.62
    POSITIVE LOGITS
     BDS
    0.99
    halla
    0.75
    ModLoader
    0.74
    NF
    0.74
    Winged
    0.71
    ECA
    0.68
     warr
    0.68
    anski
    0.66
    CHAT
    0.66
    VII
    0.66
    Activations Density 0.010%

    No Known Activations