© 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. 4-RES-JB
    11. 7369
    Prev
    Next
    INDEX
    Explanations

    mentions of Israeli settlements

    oai_token-act-pair · gpt-3.5-turbo

    references to Israeli settlements

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

    No Comments

    Negative Logits
    inx
    -0.95
    cemic
    -0.85
    emis
    -0.84
    oppy
    -0.79
    yon
    -0.79
    asus
    -0.78
    reditary
    -0.76
    enic
    -0.75
    aired
    -0.75
    onda
    -0.75
    POSITIVE LOGITS
     settlements
    1.22
     settlement
    1.13
     Settlement
    1.05
     settlers
    0.94
     bloc
    0.92
     sett
    0.91
     outpost
    0.85
     encamp
    0.82
     Sett
    0.79
     Covenant
    0.77
    Activations Density 0.012%

    No Known Activations