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

    Neuronpedia

    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. 7-RES-JB
    11. 9546
    Prev
    Next
    INDEX
    Explanations

    terms related to policies and actions regarding sanctuary cities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sanctuary cities and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.88
     Clockwork
    -0.76
     Cavern
    -0.67
     Camb
    -0.65
    unknown
    -0.64
    ,,,,
    -0.64
     Ruins
    -0.63
     Dign
    -0.63
     Helpful
    -0.62
    Amb
    -0.62
    POSITIVE LOGITS
     contracting
    0.72
     killers
    0.65
     tourism
    0.65
     voting
    0.63
    ervatives
    0.63
     camps
    0.62
     hunter
    0.62
     boarding
    0.62
    iola
    0.62
    lane
    0.61
    Activations Density 0.461%

    No Known Activations