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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 22618
    Prev
    Next
    INDEX
    Explanations

    terms related to deportation or removal of individuals from a country

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to deportation

    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
     Flavoring
    -0.85
    aque
    -0.81
    olls
    -0.75
    avez
    -0.74
    IDES
    -0.73
    ttp
    -0.73
    aber
    -0.72
    SEC
    -0.71
    Interstitial
    -0.69
    Thom
    -0.68
    POSITIVE LOGITS
     deported
    1.40
     deport
    1.16
     deportation
    1.15
     detain
    1.00
     detention
    0.86
     immigration
    0.81
     clearance
    0.81
    chwitz
    0.80
     repatri
    0.80
     scapego
    0.77
    Activations Density 0.015%

    No Known Activations