© 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. 6-RES-JB
    11. 4160
    Prev
    Next
    INDEX
    Explanations

    words related to scandals and controversies

    oai_token-act-pair · gpt-3.5-turbo

    mentions of scandals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icrobial
    -0.69
    requisite
    -0.68
    yip
    -0.66
    itar
    -0.65
    cki
    -0.64
    ramer
    -0.63
    hetics
    -0.63
    erd
    -0.62
    reens
    -0.60
    emonic
    -0.59
    POSITIVE LOGITS
     scandals
    0.98
     revolving
    0.94
     involving
    0.92
     scandal
    0.90
    ously
    0.89
    icity
    0.85
     plag
    0.84
    ous
    0.82
     allegations
    0.78
    lain
    0.74
    Activations Density 0.028%

    No Known Activations