© 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. 4-RES-JB
    11. 13280
    Prev
    Next
    INDEX
    Explanations

    keywords related to offshore financial dealings and locations

    oai_token-act-pair · gpt-3.5-turbo

    references to offshore financial practices and entities

    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
    IENCE
    -0.85
    baugh
    -0.83
    lest
    -0.79
    MQ
    -0.78
    FK
    -0.78
    Detailed
    -0.77
    ENTS
    -0.77
    Reply
    -0.77
    ============
    -0.76
    umbs
    -0.76
    POSITIVE LOGITS
     offshore
    1.12
    shore
    0.92
     drilling
    0.88
     havens
    0.88
     outsourcing
    0.87
     islands
    0.86
     wind
    0.81
    olitics
    0.76
     Graveyard
    0.76
     Panama
    0.75
    Activations Density 0.010%

    No Known Activations