© 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. 10-RES-JB
    11. 11358
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and their positions on policies or actions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of political promises or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.84
     organisers
    -0.77
     Summoner
    -0.74
     councillor
    -0.69
     Sharma
    -0.69
    OGR
    -0.67
     partName
    -0.66
     Shard
    -0.65
    rant
    -0.64
     Fn
    -0.64
    POSITIVE LOGITS
     privat
    1.08
     Medicare
    1.05
     amnesty
    1.03
     deregulation
    1.01
     taxes
    1.01
     privatization
    0.98
     tariffs
    0.95
    amacare
    0.95
     immigration
    0.93
     NAFTA
    0.92
    Activations Density 0.429%

    No Known Activations