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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-RES-JB
    6. 23532
    Prev
    Next
    INDEX
    Explanations

    phrases related to foreign individuals, particularly focusing on negative aspects such as deportation and security risks

    oai_token-act-pair · gpt-3.5-turbo

    mentions of foreigners in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     âĢ
    -0.68
     Model
    -0.65
     Blueprint
    -0.63
    PA
    -0.62
     Ramsey
    -0.62
     resolution
    -0.62
    SU
    -0.61
     journal
    -0.61
    eline
    -0.60
     model
    -0.60
    POSITIVE LOGITS
     foreigners
    3.62
     foreigner
    2.65
     Europeans
    1.88
     outsiders
    1.81
    foreign
    1.72
     tourists
    1.69
     Britons
    1.65
     Koreans
    1.59
     Malays
    1.52
     travellers
    1.51
    Activations Density 0.015%

    No Known Activations