Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 20697
    Prev
    Next
    INDEX
    Explanations

    references to the immigration and customs enforcement agency (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 @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izations
    -0.78
    orial
    -0.78
    uns
    -0.77
    velength
    -0.77
    lihood
    -0.76
    icals
    -0.76
    jac
    -0.74
    acular
    -0.71
    Downloadha
    -0.71
    orship
    -0.70
    POSITIVE LOGITS
     detain
    1.05
    ICE
    0.94
     detention
    0.92
     Detention
    0.90
     CRE
    0.90
     ICE
    0.88
    REAM
    0.88
    HAEL
    0.81
    BER
    0.78
     custody
    0.77
    Activations Density 0.021%

    No Known Activations