© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 3917
    Prev
    Next
    INDEX
    Explanations

    mentions of places or concepts related to being a sanctuary for undocumented immigrants

    oai_token-act-pair · gpt-3.5-turbo

    the term "sanctuary" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ï¸ı
    -0.79
    llor
    -0.76
    llers
    -0.75
    drive
    -0.69
     Saban
    -0.63
     monop
    -0.62
     Parsons
    -0.61
    urned
    -0.60
     Neurolog
    -0.60
    glass
    -0.60
    POSITIVE LOGITS
    ctuary
    1.52
    itary
    1.23
    ction
    1.16
    itized
    1.05
    gha
    1.04
    ctions
    1.00
    itiz
    0.99
     Francisco
    0.95
    ct
    0.93
    San
    0.93
    Activations Density 0.020%

    No Known Activations