© 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. 2349
    Prev
    Next
    INDEX
    Explanations

    items related to riot control, protests, and security measures

    oai_token-act-pair · gpt-3.5-turbo

    items and equipment associated with law enforcement or military action

    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
    EGIN
    -0.78
     Incarnation
    -0.69
    ategory
    -0.69
     Investor
    -0.68
     Dhabi
    -0.67
    eanor
    -0.67
    Commerce
    -0.67
    Appearance
    -0.65
    utenberg
    -0.64
     Commerce
    -0.63
    POSITIVE LOGITS
     shields
    1.08
    packs
    1.07
    boards
    1.07
     helmets
    1.06
    boxes
    1.05
    adders
    1.04
     markers
    1.03
    bars
    1.03
     pads
    1.03
     levers
    1.03
    Activations Density 0.461%

    No Known Activations