© 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. 6-RES-JB
    11. 7238
    Prev
    Next
    INDEX
    Explanations

    information related to rumors and news

    oai_token-act-pair · gpt-3.5-turbo

    mentions of rumors and allegations, particularly in a political context

    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
    pan
    -0.74
    uits
    -0.73
    urally
    -0.72
    alos
    -0.71
     Engineers
    -0.67
    uit
    -0.67
    ryu
    -0.66
     diseng
    -0.66
    hetics
    -0.65
    mand
    -0.65
    POSITIVE LOGITS
    Rum
    1.07
     rumours
    0.99
     rumor
    0.95
    BBC
    0.92
     rumors
    0.91
     headlines
    0.89
     TMZ
    0.88
    Leaks
    0.88
     gossip
    0.86
     sensational
    0.86
    Activations Density 0.502%

    No Known Activations