© 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. 11-RES-JB
    11. 7871
    Prev
    Next
    INDEX
    Explanations

    terms related to corporations or business activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to corporate entities and their operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icans
    -0.75
    mith
    -0.74
    lest
    -0.74
    finding
    -0.73
    imental
    -0.73
    lyn
    -0.72
    etting
    -0.72
    range
    -0.71
    theless
    -0.70
    âĵĺ
    -0.69
    POSITIVE LOGITS
     sponsorship
    1.01
     governance
    0.97
     profits
    0.94
     executives
    0.93
    porate
    0.91
     espionage
    0.88
     headquarters
    0.88
     welfare
    0.87
     greed
    0.87
     sponsors
    0.86
    Activations Density 0.047%

    No Known Activations