© 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. 4-RES-JB
    11. 14807
    Prev
    Next
    INDEX
    Explanations

    terms related to refugee issues

    oai_token-act-pair · gpt-3.5-turbo

    terms related to refugees and migrants

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

    No Comments

    Negative Logits
    aurus
    -1.18
    paces
    -1.05
    mith
    -1.02
    ynthesis
    -1.00
    cale
    -1.00
    avers
    -0.99
    orem
    -0.99
    erity
    -0.97
    ĸļ
    -0.96
    heet
    -0.96
    POSITIVE LOGITS
     Worker
    0.76
     visas
    0.74
     communities
    0.72
     tracts
    0.70
     motor
    0.70
     counts
    0.70
     visa
    0.70
     fisher
    0.68
     affairs
    0.68
     strongh
    0.68
    Activations Density 0.071%

    No Known Activations