© 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. 9-RES-JB
    11. 4652
    Prev
    Next
    INDEX
    Explanations

    conspiracy-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with conspiracy theories and related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    brance
    -0.80
    cale
    -0.70
    ynthesis
    -0.70
    someone
    -0.69
    rower
    -0.66
    urden
    -0.65
    enance
    -0.64
    ĸļ
    -0.63
     Sturgeon
    -0.62
    hirt
    -0.60
    POSITIVE LOGITS
     equivalents
    1.12
     slots
    1.11
     entries
    1.09
     variants
    1.08
     sessions
    1.08
     locations
    1.07
     instances
    1.06
     implementations
    1.06
     configurations
    1.05
     iterations
    1.05
    Activations Density 0.897%

    No Known Activations