© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9500
    Prev
    Next
    INDEX
    Explanations

    references to activities or entities related to the US Immigration and Customs Enforcement (ICE)

    oai_token-act-pair · gpt-3.5-turbo

    references to ICE (Immigration and Customs Enforcement)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orial
    -0.83
    izations
    -0.76
    amins
    -0.76
    andals
    -0.75
    uns
    -0.75
    lihood
    -0.75
    olver
    -0.73
    edom
    -0.72
    isations
    -0.72
    icals
    -0.71
    POSITIVE LOGITS
     detain
    1.09
     detention
    0.93
     Detention
    0.90
     CRE
    0.85
    REAM
    0.83
    ICE
    0.83
     ICE
    0.78
     detained
    0.76
     raids
    0.76
     custody
    0.76
    Activations Density 0.021%

    No Known Activations