© 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. 3574
    Prev
    Next
    INDEX
    Explanations

    references to law enforcement or government bodies

    oai_token-act-pair · gpt-3.5-turbo

    mentions of governmental or controlling bodies

    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
    thal
    -0.74
    ces
    -0.69
    CONT
    -0.67
    TON
    -0.67
    tom
    -0.64
    stick
    -0.63
     Candle
    -0.63
    cer
    -0.62
     Voy
    -0.62
    ted
    -0.62
    POSITIVE LOGITS
     authorities
    1.05
     Authorities
    0.94
     agencies
    0.93
     officials
    0.80
     investigating
    0.79
     tasked
    0.78
     decree
    0.78
     confir
    0.77
     raided
    0.76
     consulted
    0.75
    Activations Density 0.018%

    No Known Activations