© 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. 19688
    Prev
    Next
    INDEX
    Explanations

    mentions of criminal activities or individuals usually associated with organized crime

    oai_token-act-pair · gpt-3.5-turbo

    references to organized crime, particularly focusing on the term "mob."

    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
    éĸ
    -0.92
    ANCE
    -0.86
    ++++++++++++++++
    -0.78
    OPLE
    -0.70
    ational
    -0.67
     Excellence
    -0.66
     Dame
    -0.65
     Triangle
    -0.65
    neath
    -0.65
     Tire
    -0.64
    POSITIVE LOGITS
    sters
    1.05
    iles
    1.01
    bing
    0.97
    ographed
    0.94
    ster
    0.93
    busters
    0.88
    astic
    0.84
    ipl
    0.83
    iliar
    0.83
    oly
    0.82
    Activations Density 0.015%

    No Known Activations