© 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. 9-RES-JB
    11. 9991
    Prev
    Next
    INDEX
    Explanations

    phrases related to controversial events or conspiracy theories

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to criminal acts and conspiracy theories

    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
    Tokens
    -0.85
     narrator
    -0.71
    enhagen
    -0.68
    olor
    -0.67
    rients
    -0.67
    assies
    -0.66
    ourses
    -0.66
    then
    -0.66
    izons
    -0.66
     answ
    -0.66
    POSITIVE LOGITS
     spontaneous
    1.14
     deliberate
    1.13
     accidental
    1.10
     provocation
    1.09
     robbery
    1.09
     coincidence
    1.08
     intentional
    1.07
     malice
    1.07
     negligence
    1.06
     retaliation
    1.03
    Activations Density 0.584%

    No Known Activations