© 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. 19638
    Prev
    Next
    INDEX
    Explanations

    names related to the Abramoff scandal

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names or entities, particularly focusing on individuals and surnames

    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
    IRD
    -0.71
    ioxide
    -0.70
     Resurrection
    -0.67
     Leone
    -0.67
     barracks
    -0.64
    UFF
    -0.62
    Ùĩ
    -0.62
    Xi
    -0.61
     Sunny
    -0.60
    XT
    -0.60
    POSITIVE LOGITS
    icter
    1.02
    atta
    0.97
    opol
    0.89
    insky
    0.87
    owitz
    0.87
    stakes
    0.84
     Abram
    0.83
    strate
    0.81
    glers
    0.76
    heid
    0.75
    Activations Density 0.028%

    No Known Activations