© 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 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. 9514
    Prev
    Next
    INDEX
    Explanations

    references to "ICE" (Immigration and Customs Enforcement) - likely related to immigration enforcement activities

    oai_token-act-pair · gpt-3.5-turbo

    references to the Immigration and Customs Enforcement (ICE) agency

    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
    orship
    -0.91
    gradient
    -0.86
    angers
    -0.84
    educ
    -0.78
    andals
    -0.76
    stable
    -0.76
    orage
    -0.74
    kers
    -0.73
    authent
    -0.72
    agi
    -0.72
    POSITIVE LOGITS
    ICE
    1.27
    SEA
    0.83
    BOX
    0.82
    IRO
    0.78
     ICE
    0.78
    HAEL
    0.77
    Exit
    0.77
    PLAY
    0.74
    ODY
    0.74
    lli
    0.74
    Activations Density 0.008%

    No Known Activations