© 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. 11789
    Prev
    Next
    INDEX
    Explanations

    keywords related to financial transactions and registries

    oai_token-act-pair · gpt-3.5-turbo

    terms related to illegal activities and their consequences

    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
    manship
    -0.77
     Dome
    -0.70
    knife
    -0.69
    lift
    -0.68
    âĻ¦
    -0.67
     conditioning
    -0.67
    terday
    -0.67
     mileage
    -0.64
    theless
    -0.64
     Feast
    -0.64
    POSITIVE LOGITS
    erers
    1.46
    ered
    1.46
    ering
    1.39
    erer
    1.32
    rator
    1.06
    rative
    1.04
    ern
    1.02
    raction
    1.01
    urers
    1.01
    ries
    0.95
    Activations Density 0.071%

    No Known Activations