© 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. 3-RES-JB
    11. 7207
    Prev
    Next
    INDEX
    Explanations

    concepts related to exploitation, including labor exploitation and environmental exploitation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "exploitation" and related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gran
    -0.79
    arat
    -0.77
    cone
    -0.77
    hair
    -0.74
    upon
    -0.72
    board
    -0.68
    burst
    -0.68
    cas
    -0.65
    deb
    -0.64
    thus
    -0.64
    POSITIVE LOGITS
     exploitation
    0.93
     exploited
    0.93
    л
    0.79
    ãĥ¼ãĥĨãĤ£
    0.76
     exploiting
    0.75
    rities
    0.73
     Struggle
    0.72
    iries
    0.70
     loopholes
    0.69
     Territories
    0.68
    Activations Density 0.009%

    No Known Activations