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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 1-RES-JB
    11. 16486
    Prev
    Next
    INDEX
    Explanations

    mentions of offshore activities or entities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "offshore" and associated concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ENTS
    -0.81
    VP
    -0.77
    Brand
    -0.77
    IENCE
    -0.76
    Owner
    -0.75
    Detailed
    -0.74
    eries
    -0.74
    Reply
    -0.73
    parts
    -0.73
    ivation
    -0.72
    POSITIVE LOGITS
     offshore
    1.35
    shore
    1.11
     outsourcing
    0.98
     drilling
    0.89
     portfolio
    0.76
    apon
    0.76
     turbines
    0.74
     banking
    0.73
     wind
    0.73
     waterways
    0.72
    Activations Density 0.008%

    No Known Activations