© 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. 17580
    Prev
    Next
    INDEX
    Explanations

    terms related to national security

    oai_token-act-pair · gpt-3.5-turbo

    references to national security

    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
    chrom
    -0.80
    amaz
    -0.78
    Blocks
    -0.77
    oven
    -0.76
    ken
    -0.74
     Refresh
    -0.74
    aways
    -0.73
    Torrent
    -0.70
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.69
     Niet
    -0.68
    POSITIVE LOGITS
     adviser
    1.05
     advisor
    1.03
     Advisor
    0.86
     apparatus
    0.85
     Adviser
    0.83
    policy
    0.83
     implications
    0.81
    olitics
    0.80
     Agency
    0.80
     theorist
    0.79
    Activations Density 0.021%

    No Known Activations