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

    Neuronpedia

    Jacobian LensNEW
    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. 7890
    Prev
    Next
    INDEX
    Explanations

    conspiracies or plots involving collusion, rigging, or conspiracy theories

    oai_token-act-pair · gpt-3.5-turbo

    references to conspiracy and collusion

    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
    ains
    -0.73
    esa
    -0.70
    anse
    -0.68
    area
    -0.68
    Flo
    -0.68
    asta
    -0.67
    gain
    -0.67
    alg
    -0.67
    lication
    -0.66
    inguished
    -0.66
    POSITIVE LOGITS
     conspiring
    1.02
     collusion
    0.99
     perpetrated
    0.95
     concoct
    0.94
     blackmail
    0.93
     orchestrated
    0.93
     sabot
    0.92
    eering
    0.92
     rigged
    0.89
     sabotage
    0.88
    Activations Density 0.118%

    No Known Activations