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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 22561
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual named "Soros"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific influential individuals, particularly George Soros and Charles Koch

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seah
    -0.77
     Pats
    -0.75
    juries
    -0.71
    iencies
    -0.69
    iability
    -0.68
    iour
    -0.66
    olulu
    -0.65
    ĪĴ
    -0.65
    arers
    -0.65
    phis
    -0.64
    POSITIVE LOGITS
    ervative
    0.93
    ervatives
    0.87
    ulously
    0.84
     Unleashed
    0.80
    ulent
    0.78
    Mobil
    0.77
    bard
    0.76
     philanthrop
    0.75
     financed
    0.75
     Industries
    0.74
    Activations Density 0.111%

    No Known Activations