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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 10996
    Prev
    Next
    INDEX
    Explanations

    phrases related to immigration policies

    oai_token-act-pair · gpt-3.5-turbo

    references to political travel bans and immigration policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IPM
    -0.81
     Engels
    -0.77
     Volunte
    -0.76
     WWF
    -0.74
     Winc
    -0.72
    unicip
    -0.72
    Dialogue
    -0.70
     MLA
    -0.69
    DragonMagazine
    -0.69
     Bord
    -0.69
    POSITIVE LOGITS
    ctuary
    1.12
     visas
    1.00
     Muslims
    0.96
     Muslim
    0.89
    immigrant
    0.88
     immigrants
    0.88
    Muslim
    0.87
     undocumented
    0.85
     mosques
    0.81
     visa
    0.81
    Activations Density 0.241%

    No Known Activations